Xiaohui Shen

Zhicheng Huang, Xiaojie Jin, Chengze Lu et al.

Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty to go for making a stronger vision learner. Towards this goal, we propose Contrastive Masked Autoencoders (CMAE), a new self-supervised pre-training method for learning more comprehensive and capable vision representations. By elaboratively unifying contrastive learning (CL) and masked image model (MIM) through novel designs, CMAE leverages their respective advantages and learns representations with both strong instance discriminability and local perceptibility. Specifically, CMAE consists of two branches where the online branch is an asymmetric encoder-decoder and the momentum branch is a momentum updated encoder. During training, the online encoder reconstructs original images from latent representations of masked images to learn holistic features. The momentum encoder, fed with the full images, enhances the feature discriminability via contrastive learning with its online counterpart. To make CL compatible with MIM, CMAE introduces two new components, i.e. pixel shifting for generating plausible positive views and feature decoder for complementing features of contrastive pairs. Thanks to these novel designs, CMAE effectively improves the representation quality and transfer performance over its MIM counterpart. CMAE achieves the state-of-the-art performance on highly competitive benchmarks of image classification, semantic segmentation and object detection. Notably, CMAE-Base achieves $85.3\%$ top-1 accuracy on ImageNet and $52.5\%$ mIoU on ADE20k, surpassing previous best results by $0.7\%$ and $1.8\%$ respectively. The source code is publicly accessible at \url{https://github.com/ZhichengHuang/CMAE}.

Qihang Yu, Ju He, Xueqing Deng et al.

Open-vocabulary segmentation is a challenging task requiring segmenting and recognizing objects from an open set of categories. One way to address this challenge is to leverage multi-modal models, such as CLIP, to provide image and text features in a shared embedding space, which bridges the gap between closed-vocabulary and open-vocabulary recognition. Hence, existing methods often adopt a two-stage framework to tackle the problem, where the inputs first go through a mask generator and then through the CLIP model along with the predicted masks. This process involves extracting features from images multiple times, which can be ineffective and inefficient. By contrast, we propose to build everything into a single-stage framework using a shared Frozen Convolutional CLIP backbone, which not only significantly simplifies the current two-stage pipeline, but also remarkably yields a better accuracy-cost trade-off. The proposed FC-CLIP, benefits from the following observations: the frozen CLIP backbone maintains the ability of open-vocabulary classification and can also serve as a strong mask generator, and the convolutional CLIP generalizes well to a larger input resolution than the one used during contrastive image-text pretraining. When training on COCO panoptic data only and testing in a zero-shot manner, FC-CLIP achieve 26.8 PQ, 16.8 AP, and 34.1 mIoU on ADE20K, 18.2 PQ, 27.9 mIoU on Mapillary Vistas, 44.0 PQ, 26.8 AP, 56.2 mIoU on Cityscapes, outperforming the prior art by +4.2 PQ, +2.4 AP, +4.2 mIoU on ADE20K, +4.0 PQ on Mapillary Vistas and +20.1 PQ on Cityscapes, respectively. Additionally, the training and testing time of FC-CLIP is 7.5x and 6.6x significantly faster than the same prior art, while using 5.9x fewer parameters. FC-CLIP also sets a new state-of-the-art performance across various open-vocabulary semantic segmentation datasets. Code at https://github.com/bytedance/fc-clip

Sijie Zhu, Linjie Yang, Chen Chen et al.

Visual Place Recognition (VPR) estimates the location of query images by matching them with images in a reference database. Conventional methods generally adopt aggregated CNN features for global retrieval and RANSAC-based geometric verification for reranking. However, RANSAC only employs geometric information but ignores other possible information that could be useful for reranking, e.g. local feature correlations, and attention values. In this paper, we propose a unified place recognition framework that handles both retrieval and reranking with a novel transformer model, named $R^{2}$Former. The proposed reranking module takes feature correlation, attention value, and xy coordinates into account, and learns to determine whether the image pair is from the same location. The whole pipeline is end-to-end trainable and the reranking module alone can also be adopted on other CNN or transformer backbones as a generic component. Remarkably, $R^{2}$Former significantly outperforms state-of-the-art methods on major VPR datasets with much less inference time and memory consumption. It also achieves the state-of-the-art on the hold-out MSLS challenge set and could serve as a simple yet strong solution for real-world large-scale applications. Experiments also show vision transformer tokens are comparable and sometimes better than CNN local features on local matching. The code is released at https://github.com/Jeff-Zilence/R2Former.

Mark Weber, Lijun Yu, Qihang Yu et al.

Masked transformer models for class-conditional image generation have become a compelling alternative to diffusion models. Typically comprising two stages - an initial VQGAN model for transitioning between latent space and image space, and a subsequent Transformer model for image generation within latent space - these frameworks offer promising avenues for image synthesis. In this study, we present two primary contributions: Firstly, an empirical and systematic examination of VQGANs, leading to a modernized VQGAN. Secondly, a novel embedding-free generation network operating directly on bit tokens - a binary quantized representation of tokens with rich semantics. The first contribution furnishes a transparent, reproducible, and high-performing VQGAN model, enhancing accessibility and matching the performance of current state-of-the-art methods while revealing previously undisclosed details. The second contribution demonstrates that embedding-free image generation using bit tokens achieves a new state-of-the-art FID of 1.52 on the ImageNet 256x256 benchmark, with a compact generator model of mere 305M parameters. The code for this project is available on https://github.com/markweberdev/maskbit.

Qihang Yu, Xiaohui Shen, Liang-Chieh Chen

Localizing and recognizing objects in the open-ended physical world poses a long-standing challenge within the domain of machine perception. Recent methods have endeavored to address the issue by employing a class-agnostic mask (or box) proposal model, complemented by an open-vocabulary classifier (e.g., CLIP) using pre-extracted text embeddings. However, it is worth noting that these open-vocabulary recognition models still exhibit limitations in practical applications. On one hand, they rely on the provision of class names during testing, where the recognition performance heavily depends on this predefined set of semantic classes by users. On the other hand, when training with multiple datasets, human intervention is required to alleviate the label definition conflict between them. In this paper, we introduce the OmniScient Model (OSM), a novel Large Language Model (LLM) based mask classifier, as a straightforward and effective solution to the aforementioned challenges. Specifically, OSM predicts class labels in a generative manner, thus removing the supply of class names during both training and testing. It also enables cross-dataset training without any human interference, exhibiting robust generalization capabilities due to the world knowledge acquired from the LLM. By combining OSM with an off-the-shelf mask proposal model, we present promising results on various benchmarks, and demonstrate its effectiveness in handling novel concepts. Code/model are available at https://github.com/bytedance/OmniScient-Model.

Ju He, Qihang Yu, Inkyu Shin et al.

Video segmentation requires consistently segmenting and tracking objects over time. Due to the quadratic dependency on input size, directly applying self-attention to video segmentation with high-resolution input features poses significant challenges, often leading to insufficient GPU memory capacity. Consequently, modern video segmenters either extend an image segmenter without incorporating any temporal attention or resort to window space-time attention in a naive manner. In this work, we present Axial-VS, a general and simple framework that enhances video segmenters by tracking objects along axial trajectories. The framework tackles video segmentation through two sub-tasks: short-term within-clip segmentation and long-term cross-clip tracking. In the first step, Axial-VS augments an off-the-shelf clip-level video segmenter with the proposed axial-trajectory attention, sequentially tracking objects along the height- and width-trajectories within a clip, thereby enhancing temporal consistency by capturing motion trajectories. The axial decomposition significantly reduces the computational complexity for dense features, and outperforms the window space-time attention in segmentation quality. In the second step, we further employ axial-trajectory attention to the object queries in clip-level segmenters, which are learned to encode object information, thereby aiding object tracking across different clips and achieving consistent segmentation throughout the video. Without bells and whistles, Axial-VS showcases state-of-the-art results on video segmentation benchmarks, emphasizing its effectiveness in addressing the limitations of modern clip-level video segmenters. Code and models are available at https://github.com/TACJu/Axial-VS.

Sucheng Ren, Qihang Yu, Ju He et al.

Flow matching models have emerged as a powerful framework for realistic image generation by learning to reverse a corruption process that progressively adds Gaussian noise. However, because noise is injected in the latent domain, its impact on different frequency components is non-uniform. As a result, during inference, flow matching models tend to generate low-frequency components (global structure) in the early stages, while high-frequency components (fine details) emerge only later in the reverse process. Building on this insight, we propose Frequency-Aware Flow Matching (FreqFlow), a novel approach that explicitly incorporates frequency-aware conditioning into the flow matching framework via time-dependent adaptive weighting. We introduce a two-branch architecture: (1) a frequency branch that separately processes low- and high-frequency components to capture global structure and refine textures and edges, and (2) a spatial branch that synthesizes images in the latent domain, guided by the frequency branch's output. By explicitly integrating frequency information into the generation process, FreqFlow ensures that both large-scale coherence and fine-grained details are effectively modeled low-frequency conditioning reinforces global structure, while high-frequency conditioning enhances texture fidelity and detail sharpness. On the class-conditional ImageNet-256 generation benchmark, our method achieves state-of-the-art performance with an FID of 1.38, surpassing the prior diffusion model DiT and flow matching model SiT by 0.79 and 0.58 FID, respectively. Code is available at https://github.com/OliverRensu/FreqFlow.

FSVideo Team, Qingyu Chen, Zhiyuan Fang et al.

We introduce FSVideo, a fast speed transformer-based image-to-video (I2V) diffusion framework. We build our framework on the following key components: 1.) a new video autoencoder with highly-compressed latent space ($64\times64\times4$ spatial-temporal downsampling ratio), achieving competitive reconstruction quality; 2.) a diffusion transformer (DIT) architecture with a new layer memory design to enhance inter-layer information flow and context reuse within DIT, and 3.) a multi-resolution generation strategy via a few-step DIT upsampler to increase video fidelity. Our final model, which contains a 14B DIT base model and a 14B DIT upsampler, achieves competitive performance against other popular open-source models, while being an order of magnitude faster. We discuss our model design as well as training strategies in this report.

Qihang Yu, Ju He, Xueqing Deng et al.

This paper presents Randomized AutoRegressive modeling (RAR) for visual generation, which sets a new state-of-the-art performance on the image generation task while maintaining full compatibility with language modeling frameworks. The proposed RAR is simple: during a standard autoregressive training process with a next-token prediction objective, the input sequence-typically ordered in raster form-is randomly permuted into different factorization orders with a probability r, where r starts at 1 and linearly decays to 0 over the course of training. This annealing training strategy enables the model to learn to maximize the expected likelihood over all factorization orders and thus effectively improve the model's capability of modeling bidirectional contexts. Importantly, RAR preserves the integrity of the autoregressive modeling framework, ensuring full compatibility with language modeling while significantly improving performance in image generation. On the ImageNet-256 benchmark, RAR achieves an FID score of 1.48, not only surpassing prior state-of-the-art autoregressive image generators but also outperforming leading diffusion-based and masked transformer-based methods. Code and models will be made available at https://github.com/bytedance/1d-tokenizer

Xiaojie Jin, Bowen Zhang, Weibo Gong et al.

State-of-the-art video-text retrieval (VTR) methods typically involve fully fine-tuning a pre-trained model (e.g. CLIP) on specific datasets. However, this can result in significant storage costs in practical applications as a separate model per task must be stored. To address this issue, we present our pioneering work that enables parameter-efficient VTR using a pre-trained model, with only a small number of tunable parameters during training. Towards this goal, we propose a new method dubbed Multimodal Video Adapter (MV-Adapter) for efficiently transferring the knowledge in the pre-trained CLIP from image-text to video-text. Specifically, MV-Adapter utilizes bottleneck structures in both video and text branches, along with two novel components. The first is a Temporal Adaptation Module that is incorporated in the video branch to introduce global and local temporal contexts. We also train weights calibrations to adjust to dynamic variations across frames. The second is Cross Modality Tying that generates weights for video/text branches through sharing cross modality factors, for better aligning between modalities. Thanks to above innovations, MV-Adapter can achieve comparable or better performance than standard full fine-tuning with negligible parameters overhead. Notably, MV-Adapter consistently outperforms various competing methods in V2T/T2V tasks with large margins on five widely used VTR benchmarks (MSR-VTT, MSVD, LSMDC, DiDemo, and ActivityNet).

Sucheng Ren, Qihang Yu, Ju He et al.

Autoregressive (AR) modeling has achieved remarkable success in natural language processing by enabling models to generate text with coherence and contextual understanding through next token prediction. Recently, in image generation, VAR proposes scale-wise autoregressive modeling, which extends the next token prediction to the next scale prediction, preserving the 2D structure of images. However, VAR encounters two primary challenges: (1) its complex and rigid scale design limits generalization in next scale prediction, and (2) the generator's dependence on a discrete tokenizer with the same complex scale structure restricts modularity and flexibility in updating the tokenizer. To address these limitations, we introduce FlowAR, a general next scale prediction method featuring a streamlined scale design, where each subsequent scale is simply double the previous one. This eliminates the need for VAR's intricate multi-scale residual tokenizer and enables the use of any off-the-shelf Variational AutoEncoder (VAE). Our simplified design enhances generalization in next scale prediction and facilitates the integration of Flow Matching for high-quality image synthesis. We validate the effectiveness of FlowAR on the challenging ImageNet-256 benchmark, demonstrating superior generation performance compared to previous methods. Codes will be available at \url{https://github.com/OliverRensu/FlowAR}.

Chia-Wen Kuo, Sijie Zhu, Fan Chen et al.

Large vision-and-language models (LVLMs) have traditionally integrated visual and textual tokens by concatenating them into a single homogeneous input for large language models (LLMs), thereby maximally preserving the pre-trained language capabilities. However, this constrained architecture for visual and textual tokens restricts the design space for processing visual tokens, potentially leading to suboptimal performance and efficiency. In this paper, we propose Decomposed Attention (D-Attn), a more flexible attention architecture for LVLMs, which enables modification of visual token operations without affecting textual-to-textual attention. D-Attn decomposes the 1-D causal self-attention of LVLMs into visual-to-visual, textual-to-visual, and textual-to-textual attentions, and the visual and textual output tokens from the decomposed attentions are merged with a carefully derived weighting strategy, namely $α$-weighting. Taking advantage of the flexibility, we are able to introduce two critical improvements in visual token processing while maintaining the capacity of pre-trained LLMs: 1) We rectify the biased positional encoding in textual-to-visual attention to boost visual understanding performance. 2) We diagonalize visual-to-visual attention to reduce computation complexity from $O(|V|^2)$ to $O(|V|)$ for $|V|$ visual tokens without compromising performance. Extensive experiments and analysis validate the effectiveness of D-Attn, demonstrating significant improvements on multiple image benchmarks while significantly reducing computational costs (\eg, $5\times$ faster). Code will be available at https://github.com/bytedance/DecomposedAttention.

Vidi Team, Chia-Wen Kuo, Chuang Huang et al.

Video has emerged as the primary medium for communication and creativity on the Internet, driving strong demand for scalable, high-quality video production. Vidi models continue to evolve toward next-generation video creation and have achieved state-of-the-art performance in multimodal temporal retrieval (TR). In its second release, Vidi2 advances video understanding with fine-grained spatio-temporal grounding (STG) and extends its capability to video question answering (Video QA), enabling comprehensive multimodal reasoning. Given a text query, Vidi2 can identify not only the corresponding timestamps but also the bounding boxes of target objects within the output time ranges. To enable comprehensive evaluation of STG, we introduce a new benchmark, VUE-STG, which offers critical improvements over existing STG datasets. In addition, we upgrade the previous VUE-TR benchmark to VUE-TR-V2, achieving a more balanced duration and query distribution. Remarkably, the Vidi2 model substantially outperforms leading proprietary systems, such as Gemini 3 Pro Preview and GPT-5, on both VUE-TR-V2 and VUE-STG, while achieving competitive results with popular open-source models with similar scale on video QA benchmarks. The latest Vidi2.5 offers significantly stronger STG capability and slightly better TR and Video QA performance over Vidi2. This update also introduces a Vidi2.5-Think model to handle plot understanding with complex plot reasoning. To comprehensively evaluate the performance of plot understanding, we propose VUE-PLOT benchmark with two tracks, Character and Reasoning. Notably, Vidi2.5-Think outperforms Gemini 3 Pro Preview on fine-grained character understanding with comparable performance on complex plot reasoning. Furthermore, we demonstrate the effectiveness of Vidi2.5 on a challenging real-world application, video editing planning.

Xiaoyu Xiang, Ding Liu, Xiao Yang et al.

In this paper, we explore open-domain sketch-to-photo translation, which aims to synthesize a realistic photo from a freehand sketch with its class label, even if the sketches of that class are missing in the training data. It is challenging due to the lack of training supervision and the large geometric distortion between the freehand sketch and photo domains. To synthesize the absent freehand sketches from photos, we propose a framework that jointly learns sketch-to-photo and photo-to-sketch generation. However, the generator trained from fake sketches might lead to unsatisfying results when dealing with sketches of missing classes, due to the domain gap between synthesized sketches and real ones. To alleviate this issue, we further propose a simple yet effective open-domain sampling and optimization strategy to "fool" the generator into treating fake sketches as real ones. Our method takes advantage of the learned sketch-to-photo and photo-to-sketch mapping of in-domain data and generalizes it to the open-domain classes. We validate our method on the Scribble and SketchyCOCO datasets. Compared with the recent competing methods, our approach shows impressive results in synthesizing realistic color, texture, and maintaining the geometric composition for various categories of open-domain sketches. Our code is available at https://github.com/Mukosame/AODA

Yifan Jiang, Xinyu Gong, Ding Liu et al.

Deep learning-based methods have achieved remarkable success in image restoration and enhancement, but are they still competitive when there is a lack of paired training data? As one such example, this paper explores the low-light image enhancement problem, where in practice it is extremely challenging to simultaneously take a low-light and a normal-light photo of the same visual scene. We propose a highly effective unsupervised generative adversarial network, dubbed EnlightenGAN, that can be trained without low/normal-light image pairs, yet proves to generalize very well on various real-world test images. Instead of supervising the learning using ground truth data, we propose to regularize the unpaired training using the information extracted from the input itself, and benchmark a series of innovations for the low-light image enhancement problem, including a global-local discriminator structure, a self-regularized perceptual loss fusion, and attention mechanism. Through extensive experiments, our proposed approach outperforms recent methods under a variety of metrics in terms of visual quality and subjective user study. Thanks to the great flexibility brought by unpaired training, EnlightenGAN is demonstrated to be easily adaptable to enhancing real-world images from various domains. The code is available at \url{https://github.com/yueruchen/EnlightenGAN}

Yingwei Li, Song Bai, Cihang Xie et al.

This paper focuses on learning transferable adversarial examples specifically against defense models (models to defense adversarial attacks). In particular, we show that a simple universal perturbation can fool a series of state-of-the-art defenses. Adversarial examples generated by existing attacks are generally hard to transfer to defense models. We observe the property of regional homogeneity in adversarial perturbations and suggest that the defenses are less robust to regionally homogeneous perturbations. Therefore, we propose an effective transforming paradigm and a customized gradient transformer module to transform existing perturbations into regionally homogeneous ones. Without explicitly forcing the perturbations to be universal, we observe that a well-trained gradient transformer module tends to output input-independent gradients (hence universal) benefiting from the under-fitting phenomenon. Thorough experiments demonstrate that our work significantly outperforms the prior art attacking algorithms (either image-dependent or universal ones) by an average improvement of 14.0% when attacking 9 defenses in the transfer-based attack setting. In addition to the cross-model transferability, we also verify that regionally homogeneous perturbations can well transfer across different vision tasks (attacking with the semantic segmentation task and testing on the object detection task). The code is available here: https://github.com/LiYingwei/Regional-Homogeneity.

Jiahui Yu, Zhe Lin, Jimei Yang et al.

We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single rectangular mask are not applicable. Thus, we also present a patch-based GAN loss, named SN-PatchGAN, by applying spectral-normalized discriminator on dense image patches. SN-PatchGAN is simple in formulation, fast and stable in training. Results on automatic image inpainting and user-guided extension demonstrate that our system generates higher-quality and more flexible results than previous methods. Our system helps user quickly remove distracting objects, modify image layouts, clear watermarks and edit faces. Code, demo and models are available at: https://github.com/JiahuiYu/generative_inpainting

Jiahui Yu, Zhe Lin, Jimei Yang et al.

Recent deep learning based approaches have shown promising results for the challenging task of inpainting large missing regions in an image. These methods can generate visually plausible image structures and textures, but often create distorted structures or blurry textures inconsistent with surrounding areas. This is mainly due to ineffectiveness of convolutional neural networks in explicitly borrowing or copying information from distant spatial locations. On the other hand, traditional texture and patch synthesis approaches are particularly suitable when it needs to borrow textures from the surrounding regions. Motivated by these observations, we propose a new deep generative model-based approach which can not only synthesize novel image structures but also explicitly utilize surrounding image features as references during network training to make better predictions. The model is a feed-forward, fully convolutional neural network which can process images with multiple holes at arbitrary locations and with variable sizes during the test time. Experiments on multiple datasets including faces (CelebA, CelebA-HQ), textures (DTD) and natural images (ImageNet, Places2) demonstrate that our proposed approach generates higher-quality inpainting results than existing ones. Code, demo and models are available at: https://github.com/JiahuiYu/generative_inpainting.

Jieneng Chen, Qihang Yu, Xiaohui Shen et al.

Recent breakthroughs in vision-language models (VLMs) start a new page in the vision community. The VLMs provide stronger and more generalizable feature embeddings compared to those from ImageNet-pretrained models, thanks to the training on the large-scale Internet image-text pairs. However, despite the amazing achievement from the VLMs, vanilla Vision Transformers (ViTs) remain the default choice for the image encoder. Although pure transformer proves its effectiveness in the text encoding area, it remains questionable whether it is also the case for image encoding, especially considering that various types of networks are proposed on the ImageNet benchmark, which, unfortunately, are rarely studied in VLMs. Due to small data/model scale, the original conclusions of model design on ImageNet can be limited and biased. In this paper, we aim at building an evaluation protocol of vision models in the vision-language era under the contrastive language-image pretraining (CLIP) framework. We provide a comprehensive way to benchmark different vision models, covering their zero-shot performance and scalability in both model and training data sizes. To this end, we introduce ViTamin, a new vision models tailored for VLMs. ViTamin-L significantly outperforms ViT-L by 2.0% ImageNet zero-shot accuracy, when using the same publicly available DataComp-1B dataset and the same OpenCLIP training scheme. ViTamin-L presents promising results on 60 diverse benchmarks, including classification, retrieval, open-vocabulary detection and segmentation, and large multi-modal models. When further scaling up the model size, our ViTamin-XL with only 436M parameters attains 82.9% ImageNet zero-shot accuracy, surpassing 82.0% achieved by EVA-E that has ten times more parameters (4.4B).

Sucheng Ren, Qihang Yu, Ju He et al.

Autoregressive (AR) modeling, known for its next-token prediction paradigm, underpins state-of-the-art language and visual generative models. Traditionally, a ``token'' is treated as the smallest prediction unit, often a discrete symbol in language or a quantized patch in vision. However, the optimal token definition for 2D image structures remains an open question. Moreover, AR models suffer from exposure bias, where teacher forcing during training leads to error accumulation at inference. In this paper, we propose xAR, a generalized AR framework that extends the notion of a token to an entity X, which can represent an individual patch token, a cell (a $k\times k$ grouping of neighboring patches), a subsample (a non-local grouping of distant patches), a scale (coarse-to-fine resolution), or even a whole image. Additionally, we reformulate discrete token classification as continuous entity regression, leveraging flow-matching methods at each AR step. This approach conditions training on noisy entities instead of ground truth tokens, leading to Noisy Context Learning, which effectively alleviates exposure bias. As a result, xAR offers two key advantages: (1) it enables flexible prediction units that capture different contextual granularity and spatial structures, and (2) it mitigates exposure bias by avoiding reliance on teacher forcing. On ImageNet-256 generation benchmark, our base model, xAR-B (172M), outperforms DiT-XL/SiT-XL (675M) while achieving 20$\times$ faster inference. Meanwhile, xAR-H sets a new state-of-the-art with an FID of 1.24, running 2.2$\times$ faster than the previous best-performing model without relying on vision foundation modules (e.g., DINOv2) or advanced guidance interval sampling.

Dongwon Kim, Ju He, Qihang Yu et al.

Image tokenizers form the foundation of modern text-to-image generative models but are notoriously difficult to train. Furthermore, most existing text-to-image models rely on large-scale, high-quality private datasets, making them challenging to replicate. In this work, we introduce Text-Aware Transformer-based 1-Dimensional Tokenizer (TA-TiTok), an efficient and powerful image tokenizer that can utilize either discrete or continuous 1-dimensional tokens. TA-TiTok uniquely integrates textual information during the tokenizer decoding stage (i.e., de-tokenization), accelerating convergence and enhancing performance. TA-TiTok also benefits from a simplified, yet effective, one-stage training process, eliminating the need for the complex two-stage distillation used in previous 1-dimensional tokenizers. This design allows for seamless scalability to large datasets. Building on this, we introduce a family of text-to-image Masked Generative Models (MaskGen), trained exclusively on open data while achieving comparable performance to models trained on private data. We aim to release both the efficient, strong TA-TiTok tokenizers and the open-data, open-weight MaskGen models to promote broader access and democratize the field of text-to-image masked generative models.

Chenglin Yang, Celong Liu, Xueqing Deng et al.

We present 1.58-bit FLUX, the first successful approach to quantizing the state-of-the-art text-to-image generation model, FLUX.1-dev, using 1.58-bit weights (i.e., values in {-1, 0, +1}) while maintaining comparable performance for generating 1024 x 1024 images. Notably, our quantization method operates without access to image data, relying solely on self-supervision from the FLUX.1-dev model. Additionally, we develop a custom kernel optimized for 1.58-bit operations, achieving a 7.7x reduction in model storage, a 5.1x reduction in inference memory, and improved inference latency. Extensive evaluations on the GenEval and T2I Compbench benchmarks demonstrate the effectiveness of 1.58-bit FLUX in maintaining generation quality while significantly enhancing computational efficiency.

Xueqing Deng, Qihang Yu, Peng Wang et al.

In recent decades, the vision community has witnessed remarkable progress in visual recognition, partially owing to advancements in dataset benchmarks. Notably, the established COCO benchmark has propelled the development of modern detection and segmentation systems. However, the COCO segmentation benchmark has seen comparatively slow improvement over the last decade. Originally equipped with coarse polygon annotations for thing instances, it gradually incorporated coarse superpixel annotations for stuff regions, which were subsequently heuristically amalgamated to yield panoptic segmentation annotations. These annotations, executed by different groups of raters, have resulted not only in coarse segmentation masks but also in inconsistencies between segmentation types. In this study, we undertake a comprehensive reevaluation of the COCO segmentation annotations. By enhancing the annotation quality and expanding the dataset to encompass 383K images with more than 5.18M panoptic masks, we introduce COCONut, the COCO Next Universal segmenTation dataset. COCONut harmonizes segmentation annotations across semantic, instance, and panoptic segmentation with meticulously crafted high-quality masks, and establishes a robust benchmark for all segmentation tasks. To our knowledge, COCONut stands as the inaugural large-scale universal segmentation dataset, verified by human raters. We anticipate that the release of COCONut will significantly contribute to the community's ability to assess the progress of novel neural networks.

Xueqing Deng, Qihang Yu, Ali Athar et al.

This paper introduces the COCONut-PanCap dataset, created to enhance panoptic segmentation and grounded image captioning. Building upon the COCO dataset with advanced COCONut panoptic masks, this dataset aims to overcome limitations in existing image-text datasets that often lack detailed, scene-comprehensive descriptions. The COCONut-PanCap dataset incorporates fine-grained, region-level captions grounded in panoptic segmentation masks, ensuring consistency and improving the detail of generated captions. Through human-edited, densely annotated descriptions, COCONut-PanCap supports improved training of vision-language models (VLMs) for image understanding and generative models for text-to-image tasks. Experimental results demonstrate that COCONut-PanCap significantly boosts performance across understanding and generation tasks, offering complementary benefits to large-scale datasets. This dataset sets a new benchmark for evaluating models on joint panoptic segmentation and grounded captioning tasks, addressing the need for high-quality, detailed image-text annotations in multi-modal learning.

Vidi Team, Celong Liu, Chia-Wen Kuo et al.

Humans naturally share information with those they are connected to, and video has become one of the dominant mediums for communication and expression on the Internet. To support the creation of high-quality large-scale video content, a modern pipeline requires a comprehensive understanding of both the raw input materials (e.g., the unedited footage captured by cameras) and the editing components (e.g., visual effects). In video editing scenarios, models must process multiple modalities (e.g., vision, audio, text) with strong background knowledge and handle flexible input lengths (e.g., hour-long raw videos), which poses significant challenges for traditional models. In this report, we introduce Vidi, a family of Large Multimodal Models (LMMs) for a wide range of video understand editing scenarios. The first release focuses on temporal retrieval, i.e., identifying the time ranges within the input videos corresponding to a given text query, which plays a critical role in intelligent editing. The model is capable of processing hour-long videos with strong temporal understanding capability, e.g., retrieve time ranges for certain queries. To support a comprehensive evaluation in real-world scenarios, we also present the VUE-TR benchmark, which introduces five key advancements. 1) Video duration: significantly longer than videos of existing temporal retrival datasets, 2) Audio support: includes audio-based queries, 3) Query format: diverse query lengths/formats, 4) Annotation quality: ground-truth time ranges are manually annotated. 5) Evaluation metric: a refined IoU metric to support evaluation over multiple time ranges. Remarkably, Vidi significantly outperforms leading proprietary models, e.g., GPT-4o and Gemini, on the temporal retrieval task, indicating its superiority in video editing scenarios.

Qihao Liu, Zhanpeng Zeng, Ju He et al.

This paper presents innovative enhancements to diffusion models by integrating a novel multi-resolution network and time-dependent layer normalization. Diffusion models have gained prominence for their effectiveness in high-fidelity image generation. While conventional approaches rely on convolutional U-Net architectures, recent Transformer-based designs have demonstrated superior performance and scalability. However, Transformer architectures, which tokenize input data (via "patchification"), face a trade-off between visual fidelity and computational complexity due to the quadratic nature of self-attention operations concerning token length. While larger patch sizes enable attention computation efficiency, they struggle to capture fine-grained visual details, leading to image distortions. To address this challenge, we propose augmenting the Diffusion model with the Multi-Resolution network (DiMR), a framework that refines features across multiple resolutions, progressively enhancing detail from low to high resolution. Additionally, we introduce Time-Dependent Layer Normalization (TD-LN), a parameter-efficient approach that incorporates time-dependent parameters into layer normalization to inject time information and achieve superior performance. Our method's efficacy is demonstrated on the class-conditional ImageNet generation benchmark, where DiMR-XL variants outperform prior diffusion models, setting new state-of-the-art FID scores of 1.70 on ImageNet 256 x 256 and 2.89 on ImageNet 512 x 512. Project page: https://qihao067.github.io/projects/DiMR

Qihang Yu, Mark Weber, Xueqing Deng et al.

Recent advancements in generative models have highlighted the crucial role of image tokenization in the efficient synthesis of high-resolution images. Tokenization, which transforms images into latent representations, reduces computational demands compared to directly processing pixels and enhances the effectiveness and efficiency of the generation process. Prior methods, such as VQGAN, typically utilize 2D latent grids with fixed downsampling factors. However, these 2D tokenizations face challenges in managing the inherent redundancies present in images, where adjacent regions frequently display similarities. To overcome this issue, we introduce Transformer-based 1-Dimensional Tokenizer (TiTok), an innovative approach that tokenizes images into 1D latent sequences. TiTok provides a more compact latent representation, yielding substantially more efficient and effective representations than conventional techniques. For example, a 256 x 256 x 3 image can be reduced to just 32 discrete tokens, a significant reduction from the 256 or 1024 tokens obtained by prior methods. Despite its compact nature, TiTok achieves competitive performance to state-of-the-art approaches. Specifically, using the same generator framework, TiTok attains 1.97 gFID, outperforming MaskGIT baseline significantly by 4.21 at ImageNet 256 x 256 benchmark. The advantages of TiTok become even more significant when it comes to higher resolution. At ImageNet 512 x 512 benchmark, TiTok not only outperforms state-of-the-art diffusion model DiT-XL/2 (gFID 2.74 vs. 3.04), but also reduces the image tokens by 64x, leading to 410x faster generation process. Our best-performing variant can significantly surpasses DiT-XL/2 (gFID 2.13 vs. 3.04) while still generating high-quality samples 74x faster.

Inkyu Shin, Qihang Yu, Xiaohui Shen et al.

Recent advancements in zero-shot video diffusion models have shown promise for text-driven video editing, but challenges remain in achieving high temporal consistency. To address this, we introduce Video-3DGS, a 3D Gaussian Splatting (3DGS)-based video refiner designed to enhance temporal consistency in zero-shot video editors. Our approach utilizes a two-stage 3D Gaussian optimizing process tailored for editing dynamic monocular videos. In the first stage, Video-3DGS employs an improved version of COLMAP, referred to as MC-COLMAP, which processes original videos using a Masked and Clipped approach. For each video clip, MC-COLMAP generates the point clouds for dynamic foreground objects and complex backgrounds. These point clouds are utilized to initialize two sets of 3D Gaussians (Frg-3DGS and Bkg-3DGS) aiming to represent foreground and background views. Both foreground and background views are then merged with a 2D learnable parameter map to reconstruct full views. In the second stage, we leverage the reconstruction ability developed in the first stage to impose the temporal constraints on the video diffusion model. To demonstrate the efficacy of Video-3DGS on both stages, we conduct extensive experiments across two related tasks: Video Reconstruction and Video Editing. Video-3DGS trained with 3k iterations significantly improves video reconstruction quality (+3 PSNR, +7 PSNR increase) and training efficiency (x1.9, x4.5 times faster) over NeRF-based and 3DGS-based state-of-art methods on DAVIS dataset, respectively. Moreover, it enhances video editing by ensuring temporal consistency across 58 dynamic monocular videos.

Yichun Shi, Xiao Yang, Yangyue Wan et al.

Recent studies have shown that StyleGANs provide promising prior models for downstream tasks on image synthesis and editing. However, since the latent codes of StyleGANs are designed to control global styles, it is hard to achieve a fine-grained control over synthesized images. We present SemanticStyleGAN, where a generator is trained to model local semantic parts separately and synthesizes images in a compositional way. The structure and texture of different local parts are controlled by corresponding latent codes. Experimental results demonstrate that our model provides a strong disentanglement between different spatial areas. When combined with editing methods designed for StyleGANs, it can achieve a more fine-grained control to edit synthesized or real images. The model can also be extended to other domains via transfer learning. Thus, as a generic prior model with built-in disentanglement, it could facilitate the development of GAN-based applications and enable more potential downstream tasks.

Yi-Wen Chen, Xiaojie Jin, Xiaohui Shen et al.

Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neural networks or optical flow. However, these approaches require high computational cost, and tend to accumulate inaccuracies over time. In this paper, we propose a network with attention modules to learn contrastive features for video salient object detection without the high computational temporal modeling techniques. We develop a non-local self-attention scheme to capture the global information in the video frame. A co-attention formulation is utilized to combine the low-level and high-level features. We further apply the contrastive learning to improve the feature representations, where foreground region pairs from the same video are pulled together, and foreground-background region pairs are pushed away in the latent space. The intra-frame contrastive loss helps separate the foreground and background features, and the inter-frame contrastive loss improves the temporal consistency. We conduct extensive experiments on several benchmark datasets for video salient object detection and unsupervised video object segmentation, and show that the proposed method requires less computation, and performs favorably against the state-of-the-art approaches.

Yifan Wang, Linjie Luo, Xiaohui Shen et al.

Recently, significant progress has been made in single-view depth estimation thanks to increasingly large and diverse depth datasets. However, these datasets are largely limited to specific application domains (e.g. indoor, autonomous driving) or static in-the-wild scenes due to hardware constraints or technical limitations of 3D reconstruction. In this paper, we introduce the first depth dataset DynOcc consisting of dynamic in-the-wild scenes. Our approach leverages the occlusion cues in these dynamic scenes to infer depth relationships between points of selected video frames. To achieve accurate occlusion detection and depth order estimation, we employ a novel occlusion boundary detection, filtering and thinning scheme followed by a robust foreground/background classification method. In total our DynOcc dataset contains 22M depth pairs out of 91K frames from a diverse set of videos. Using our dataset we achieved state-of-the-art results measured in weighted human disagreement rate (WHDR). We also show that the inferred depth maps trained with DynOcc can preserve sharper depth boundaries.

Wei Xiong, Ding Liu, Xiaohui Shen et al.

In this paper, we tackle the problem of enhancing real-world low-light images with significant noise in an unsupervised fashion. Conventional unsupervised learning-based approaches usually tackle the low-light image enhancement problem using an image-to-image translation model. They focus primarily on illumination or contrast enhancement but fail to suppress the noise that ubiquitously exists in images taken under real-world low-light conditions. To address this issue, we explicitly decouple this task into two sub-tasks: illumination enhancement and noise suppression. We propose to learn a two-stage GAN-based framework to enhance the real-world low-light images in a fully unsupervised fashion. To facilitate the unsupervised training of our model, we construct samples with pseudo labels. Furthermore, we propose an adaptive content loss to suppress real image noise in different regions based on illumination intensity. In addition to conventional benchmark datasets, a new unpaired low-light image enhancement dataset is built and used to thoroughly evaluate the performance of our model. Extensive experiments show that our proposed method outperforms the state-of-the-art unsupervised image enhancement methods in terms of both illumination enhancement and noise reduction.

Jian Ren, Menglei Chai, Sergey Tulyakov et al.

In this paper, we tackle the problem of human motion transfer, where we synthesize novel motion video for a target person that imitates the movement from a reference video. It is a video-to-video translation task in which the estimated poses are used to bridge two domains. Despite substantial progress on the topic, there exist several problems with the previous methods. First, there is a domain gap between training and testing pose sequences--the model is tested on poses it has not seen during training, such as difficult dancing moves. Furthermore, pose detection errors are inevitable, making the job of the generator harder. Finally, generating realistic pixels from sparse poses is challenging in a single step. To address these challenges, we introduce a novel pose-to-video translation framework for generating high-quality videos that are temporally coherent even for in-the-wild pose sequences unseen during training. We propose a pose augmentation method to minimize the training-test gap, a unified paired and unpaired learning strategy to improve the robustness to detection errors, and two-stage network architecture to achieve superior texture quality. To further boost research on the topic, we build two human motion datasets. Finally, we show the superiority of our approach over the state-of-the-art studies through extensive experiments and evaluations on different datasets.

Tianlang Chen, Chen Fang, Xiaohui Shen et al.

In this work, we propose a new solution to 3D human pose estimation in videos. Instead of directly regressing the 3D joint locations, we draw inspiration from the human skeleton anatomy and decompose the task into bone direction prediction and bone length prediction, from which the 3D joint locations can be completely derived. Our motivation is the fact that the bone lengths of a human skeleton remain consistent across time. This promotes us to develop effective techniques to utilize global information across all the frames in a video for high-accuracy bone length prediction. Moreover, for the bone direction prediction network, we propose a fully-convolutional propagating architecture with long skip connections. Essentially, it predicts the directions of different bones hierarchically without using any time-consuming memory units e.g. LSTM). A novel joint shift loss is further introduced to bridge the training of the bone length and bone direction prediction networks. Finally, we employ an implicit attention mechanism to feed the 2D keypoint visibility scores into the model as extra guidance, which significantly mitigates the depth ambiguity in many challenging poses. Our full model outperforms the previous best results on Human3.6M and MPI-INF-3DHP datasets, where comprehensive evaluation validates the effectiveness of our model.

Haoye Dong, Xiaodan Liang, Yixuan Zhang et al.

Interactive fashion image manipulation, which enables users to edit images with sketches and color strokes, is an interesting research problem with great application value. Existing works often treat it as a general inpainting task and do not fully leverage the semantic structural information in fashion images. Moreover, they directly utilize conventional convolution and normalization layers to restore the incomplete image, which tends to wash away the sketch and color information. In this paper, we propose a novel Fashion Editing Generative Adversarial Network (FE-GAN), which is capable of manipulating fashion images by free-form sketches and sparse color strokes. FE-GAN consists of two modules: 1) a free-form parsing network that learns to control the human parsing generation by manipulating sketch and color; 2) a parsing-aware inpainting network that renders detailed textures with semantic guidance from the human parsing map. A new attention normalization layer is further applied at multiple scales in the decoder of the inpainting network to enhance the quality of the synthesized image. Extensive experiments on high-resolution fashion image datasets demonstrate that the proposed method significantly outperforms the state-of-the-art methods on image manipulation.

Ke Gong, Yiming Gao, Xiaodan Liang et al.

Prior highly-tuned human parsing models tend to fit towards each dataset in a specific domain or with discrepant label granularity, and can hardly be adapted to other human parsing tasks without extensive re-training. In this paper, we aim to learn a single universal human parsing model that can tackle all kinds of human parsing needs by unifying label annotations from different domains or at various levels of granularity. This poses many fundamental learning challenges, e.g. discovering underlying semantic structures among different label granularity, performing proper transfer learning across different image domains, and identifying and utilizing label redundancies across related tasks. To address these challenges, we propose a new universal human parsing agent, named "Graphonomy", which incorporates hierarchical graph transfer learning upon the conventional parsing network to encode the underlying label semantic structures and propagate relevant semantic information. In particular, Graphonomy first learns and propagates compact high-level graph representation among the labels within one dataset via Intra-Graph Reasoning, and then transfers semantic information across multiple datasets via Inter-Graph Transfer. Various graph transfer dependencies (\eg, similarity, linguistic knowledge) between different datasets are analyzed and encoded to enhance graph transfer capability. By distilling universal semantic graph representation to each specific task, Graphonomy is able to predict all levels of parsing labels in one system without piling up the complexity. Experimental results show Graphonomy effectively achieves the state-of-the-art results on three human parsing benchmarks as well as advantageous universal human parsing performance.

Lijun Wang, Xiaohui Shen, Jianming Zhang et al.

We aim to generate high resolution shallow depth-of-field (DoF) images from a single all-in-focus image with controllable focal distance and aperture size. To achieve this, we propose a novel neural network model comprised of a depth prediction module, a lens blur module, and a guided upsampling module. All modules are differentiable and are learned from data. To train our depth prediction module, we collect a dataset of 2462 RGB-D images captured by mobile phones with a dual-lens camera, and use existing segmentation datasets to improve border prediction. We further leverage a synthetic dataset with known depth to supervise the lens blur and guided upsampling modules. The effectiveness of our system and training strategies are verified in the experiments. Our method can generate high-quality shallow DoF images at high resolution, and produces significantly fewer artifacts than the baselines and existing solutions for single image shallow DoF synthesis. Compared with the iPhone portrait mode, which is a state-of-the-art shallow DoF solution based on a dual-lens depth camera, our method generates comparable results, while allowing for greater flexibility to choose focal points and aperture size, and is not limited to one capture setup.

Yufei Wang, Zhe Lin, Xiaohui Shen et al.

Existing works on semantic segmentation typically consider a small number of labels, ranging from tens to a few hundreds. With a large number of labels, training and evaluation of such task become extremely challenging due to correlation between labels and lack of datasets with complete annotations. We formulate semantic segmentation as a problem of image segmentation given a semantic concept, and propose a novel system which can potentially handle an unlimited number of concepts, including objects, parts, stuff, and attributes. We achieve this using a weakly and semi-supervised framework leveraging multiple datasets with different levels of supervision. We first train a deep neural network on a 6M stock image dataset with only image-level labels to learn visual-semantic embedding on 18K concepts. Then, we refine and extend the embedding network to predict an attention map, using a curated dataset with bounding box annotations on 750 concepts. Finally, we train an attention-driven class agnostic segmentation network using an 80-category fully annotated dataset. We perform extensive experiments to validate that the proposed system performs competitively to the state of the art on fully supervised concepts, and is capable of producing accurate segmentations for weakly learned and unseen concepts.

Xiangyun Zhao, Haoxiang Li, Xiaohui Shen et al.

Multi-task learning has been widely adopted in many computer vision tasks to improve overall computation efficiency or boost the performance of individual tasks, under the assumption that those tasks are correlated and complementary to each other. However, the relationships between the tasks are complicated in practice, especially when the number of involved tasks scales up. When two tasks are of weak relevance, they may compete or even distract each other during joint training of shared parameters, and as a consequence undermine the learning of all the tasks. This will raise destructive interference which decreases learning efficiency of shared parameters and lead to low quality loss local optimum w.r.t. shared parameters. To address the this problem, we propose a general modulation module, which can be inserted into any convolutional neural network architecture, to encourage the coupling and feature sharing of relevant tasks while disentangling the learning of irrelevant tasks with minor parameters addition. Equipped with this module, gradient directions from different tasks can be enforced to be consistent for those shared parameters, which benefits multi-task joint training. The module is end-to-end learnable without ad-hoc design for specific tasks, and can naturally handle many tasks at the same time. We apply our approach on two retrieval tasks, face retrieval on the CelebA dataset [1] and product retrieval on the UT-Zappos50K dataset [2, 3], and demonstrate its advantage over other multi-task learning methods in both accuracy and storage efficiency.

Bangjie Yin, Luan Tran, Haoxiang Li et al.

Deep CNNs have been pushing the frontier of visual recognition over past years. Besides recognition accuracy, strong demands in understanding deep CNNs in the research community motivate developments of tools to dissect pre-trained models to visualize how they make predictions. Recent works further push the interpretability in the network learning stage to learn more meaningful representations. In this work, focusing on a specific area of visual recognition, we report our efforts towards interpretable face recognition. We propose a spatial activation diversity loss to learn more structured face representations. By leveraging the structure, we further design a feature activation diversity loss to push the interpretable representations to be discriminative and robust to occlusions. We demonstrate on three face recognition benchmarks that our proposed method is able to improve face recognition accuracy with easily interpretable face representations.

Xiaodan Liang, Ke Gong, Xiaohui Shen et al.

Human parsing and pose estimation have recently received considerable interest due to their substantial application potentials. However, the existing datasets have limited numbers of images and annotations and lack a variety of human appearances and coverage of challenging cases in unconstrained environments. In this paper, we introduce a new benchmark named "Look into Person (LIP)" that provides a significant advancement in terms of scalability, diversity, and difficulty, which are crucial for future developments in human-centric analysis. This comprehensive dataset contains over 50,000 elaborately annotated images with 19 semantic part labels and 16 body joints, which are captured from a broad range of viewpoints, occlusions, and background complexities. Using these rich annotations, we perform detailed analyses of the leading human parsing and pose estimation approaches, thereby obtaining insights into the successes and failures of these methods. To further explore and take advantage of the semantic correlation of these two tasks, we propose a novel joint human parsing and pose estimation network to explore efficient context modeling, which can simultaneously predict parsing and pose with extremely high quality. Furthermore, we simplify the network to solve human parsing by exploring a novel self-supervised structure-sensitive learning approach, which imposes human pose structures into the parsing results without resorting to extra supervision. The dataset, code and models are available at http://www.sysu-hcp.net/lip/.

Licheng Yu, Zhe Lin, Xiaohui Shen et al.

In this paper, we address referring expression comprehension: localizing an image region described by a natural language expression. While most recent work treats expressions as a single unit, we propose to decompose them into three modular components related to subject appearance, location, and relationship to other objects. This allows us to flexibly adapt to expressions containing different types of information in an end-to-end framework. In our model, which we call the Modular Attention Network (MAttNet), two types of attention are utilized: language-based attention that learns the module weights as well as the word/phrase attention that each module should focus on; and visual attention that allows the subject and relationship modules to focus on relevant image components. Module weights combine scores from all three modules dynamically to output an overall score. Experiments show that MAttNet outperforms previous state-of-art methods by a large margin on both bounding-box-level and pixel-level comprehension tasks. Demo and code are provided.

Xiaojie Jin, Huaxin Xiao, Xiaohui Shen et al.

The ability of predicting the future is important for intelligent systems, e.g. autonomous vehicles and robots to plan early and make decisions accordingly. Future scene parsing and optical flow estimation are two key tasks that help agents better understand their environments as the former provides dense semantic information, i.e. what objects will be present and where they will appear, while the latter provides dense motion information, i.e. how the objects will move. In this paper, we propose a novel model to simultaneously predict scene parsing and optical flow in unobserved future video frames. To our best knowledge, this is the first attempt in jointly predicting scene parsing and motion dynamics. In particular, scene parsing enables structured motion prediction by decomposing optical flow into different groups while optical flow estimation brings reliable pixel-wise correspondence to scene parsing. By exploiting this mutually beneficial relationship, our model shows significantly better parsing and motion prediction results when compared to well-established baselines and individual prediction models on the large-scale Cityscapes dataset. In addition, we also demonstrate that our model can be used to predict the steering angle of the vehicles, which further verifies the ability of our model to learn latent representations of scene dynamics.

Wei-Chih Hung, Yi-Hsuan Tsai, Xiaohui Shen et al.

We present a scene parsing method that utilizes global context information based on both the parametric and non- parametric models. Compared to previous methods that only exploit the local relationship between objects, we train a context network based on scene similarities to generate feature representations for global contexts. In addition, these learned features are utilized to generate global and spatial priors for explicit classes inference. We then design modules to embed the feature representations and the priors into the segmentation network as additional global context cues. We show that the proposed method can eliminate false positives that are not compatible with the global context representations. Experiments on both the MIT ADE20K and PASCAL Context datasets show that the proposed method performs favorably against existing methods.

Xiaodan Liang, Yunchao Wei, Liang Lin et al.

An intuition on human segmentation is that when a human is moving in a video, the video-context (e.g., appearance and motion clues) may potentially infer reasonable mask information for the whole human body. Inspired by this, based on popular deep convolutional neural networks (CNN), we explore a very-weakly supervised learning framework for human segmentation task, where only an imperfect human detector is available along with massive weakly-labeled YouTube videos. In our solution, the video-context guided human mask inference and CNN based segmentation network learning iterate to mutually enhance each other until no further improvement gains. In the first step, each video is decomposed into supervoxels by the unsupervised video segmentation. The superpixels within the supervoxels are then classified as human or non-human by graph optimization with unary energies from the imperfect human detection results and the predicted confidence maps by the CNN trained in the previous iteration. In the second step, the video-context derived human masks are used as direct labels to train CNN. Extensive experiments on the challenging PASCAL VOC 2012 semantic segmentation benchmark demonstrate that the proposed framework has already achieved superior results than all previous weakly-supervised methods with object class or bounding box annotations. In addition, by augmenting with the annotated masks from PASCAL VOC 2012, our method reaches a new state-of-the-art performance on the human segmentation task.

Xin Li, Zequn Jie, Wei Wang et al.

Parsing urban scene images benefits many applications, especially self-driving. Most of the current solutions employ generic image parsing models that treat all scales and locations in the images equally and do not consider the geometry property of car-captured urban scene images. Thus, they suffer from heterogeneous object scales caused by perspective projection of cameras on actual scenes and inevitably encounter parsing failures on distant objects as well as other boundary and recognition errors. In this work, we propose a new FoveaNet model to fully exploit the perspective geometry of scene images and address the common failures of generic parsing models. FoveaNet estimates the perspective geometry of a scene image through a convolutional network which integrates supportive evidence from contextual objects within the image. Based on the perspective geometry information, FoveaNet "undoes" the camera perspective projection analyzing regions in the space of the actual scene, and thus provides much more reliable parsing results. Furthermore, to effectively address the recognition errors, FoveaNet introduces a new dense CRFs model that takes the perspective geometry as a prior potential. We evaluate FoveaNet on two urban scene parsing datasets, Cityspaces and CamVid, which demonstrates that FoveaNet can outperform all the well-established baselines and provide new state-of-the-art performance.

Yufei Wang, Zhe Lin, Xiaohui Shen et al.

Automatic organization of personal photos is a problem with many real world ap- plications, and can be divided into two main tasks: recognizing the event type of the photo collection, and selecting interesting images from the collection. In this paper, we attempt to simultaneously solve both tasks: album-wise event recognition and image- wise importance prediction. We collected an album dataset with both event type labels and image importance labels, refined from an existing CUFED dataset. We propose a hybrid system consisting of three parts: A siamese network-based event-specific image importance prediction, a Convolutional Neural Network (CNN) that recognizes the event type, and a Long Short-Term Memory (LSTM)-based sequence level event recognizer. We propose an iterative updating procedure for event type and image importance score prediction. We experimentally verified that image importance score prediction and event type recognition can each help the performance of the other.

Yufei Wang, Zhe Lin, Xiaohui Shen et al.

Recently, there has been a lot of interest in automatically generating descriptions for an image. Most existing language-model based approaches for this task learn to generate an image description word by word in its original word order. However, for humans, it is more natural to locate the objects and their relationships first, and then elaborate on each object, describing notable attributes. We present a coarse-to-fine method that decomposes the original image description into a skeleton sentence and its attributes, and generates the skeleton sentence and attribute phrases separately. By this decomposition, our method can generate more accurate and novel descriptions than the previous state-of-the-art. Experimental results on the MS-COCO and a larger scale Stock3M datasets show that our algorithm yields consistent improvements across different evaluation metrics, especially on the SPICE metric, which has much higher correlation with human ratings than the conventional metrics. Furthermore, our algorithm can generate descriptions with varied length, benefiting from the separate control of the skeleton and attributes. This enables image description generation that better accommodates user preferences.

Marc-André Gardner, Kalyan Sunkavalli, Ersin Yumer et al.

We propose an automatic method to infer high dynamic range illumination from a single, limited field-of-view, low dynamic range photograph of an indoor scene. In contrast to previous work that relies on specialized image capture, user input, and/or simple scene models, we train an end-to-end deep neural network that directly regresses a limited field-of-view photo to HDR illumination, without strong assumptions on scene geometry, material properties, or lighting. We show that this can be accomplished in a three step process: 1) we train a robust lighting classifier to automatically annotate the location of light sources in a large dataset of LDR environment maps, 2) we use these annotations to train a deep neural network that predicts the location of lights in a scene from a single limited field-of-view photo, and 3) we fine-tune this network using a small dataset of HDR environment maps to predict light intensities. This allows us to automatically recover high-quality HDR illumination estimates that significantly outperform previous state-of-the-art methods. Consequently, using our illumination estimates for applications like 3D object insertion, we can achieve results that are photo-realistic, which is validated via a perceptual user study.

Chenxi Liu, Zhe Lin, Xiaohui Shen et al.

In this paper we are interested in the problem of image segmentation given natural language descriptions, i.e. referring expressions. Existing works tackle this problem by first modeling images and sentences independently and then segment images by combining these two types of representations. We argue that learning word-to-image interaction is more native in the sense of jointly modeling two modalities for the image segmentation task, and we propose convolutional multimodal LSTM to encode the sequential interactions between individual words, visual information, and spatial information. We show that our proposed model outperforms the baseline model on benchmark datasets. In addition, we analyze the intermediate output of the proposed multimodal LSTM approach and empirically explain how this approach enforces a more effective word-to-image interaction.