Xinlong Wang

Yuxin Fang, Wen Wang, Binhui Xie et al. · meta-ai

We launch EVA, a vision-centric foundation model to explore the limits of visual representation at scale using only publicly accessible data. EVA is a vanilla ViT pre-trained to reconstruct the masked out image-text aligned vision features conditioned on visible image patches. Via this pretext task, we can efficiently scale up EVA to one billion parameters, and sets new records on a broad range of representative vision downstream tasks, such as image recognition, video action recognition, object detection, instance segmentation and semantic segmentation without heavy supervised training. Moreover, we observe quantitative changes in scaling EVA result in qualitative changes in transfer learning performance that are not present in other models. For instance, EVA takes a great leap in the challenging large vocabulary instance segmentation task: our model achieves almost the same state-of-the-art performance on LVISv1.0 dataset with over a thousand categories and COCO dataset with only eighty categories. Beyond a pure vision encoder, EVA can also serve as a vision-centric, multi-modal pivot to connect images and text. We find initializing the vision tower of a giant CLIP from EVA can greatly stabilize the training and outperform the training from scratch counterpart with much fewer samples and less compute, providing a new direction for scaling up and accelerating the costly training of multi-modal foundation models. To facilitate future research, we release all the code and models at https://github.com/baaivision/EVA.

Quan Sun, Yuxin Fang, Ledell Wu et al. · meta-ai

Contrastive language-image pre-training, CLIP for short, has gained increasing attention for its potential in various scenarios. In this paper, we propose EVA-CLIP, a series of models that significantly improve the efficiency and effectiveness of CLIP training. Our approach incorporates new techniques for representation learning, optimization, and augmentation, enabling EVA-CLIP to achieve superior performance compared to previous CLIP models with the same number of parameters but significantly smaller training costs. Notably, our largest 5.0B-parameter EVA-02-CLIP-E/14+ with only 9 billion seen samples achieves 82.0 zero-shot top-1 accuracy on ImageNet-1K val. A smaller EVA-02-CLIP-L/14+ with only 430 million parameters and 6 billion seen samples achieves 80.4 zero-shot top-1 accuracy on ImageNet-1K val. To facilitate open access and open research, we release the complete suite of EVA-CLIP to the community at https://github.com/baaivision/EVA/tree/master/EVA-CLIP.

Yuxin Fang, Quan Sun, Xinggang Wang et al.

We launch EVA-02, a next-generation Transformer-based visual representation pre-trained to reconstruct strong and robust language-aligned vision features via masked image modeling. With an updated plain Transformer architecture as well as extensive pre-training from an open & accessible giant CLIP vision encoder, EVA-02 demonstrates superior performance compared to prior state-of-the-art approaches across various representative vision tasks, while utilizing significantly fewer parameters and compute budgets. Notably, using exclusively publicly accessible training data, EVA-02 with only 304M parameters achieves a phenomenal 90.0 fine-tuning top-1 accuracy on ImageNet-1K val set. Additionally, our EVA-02-CLIP can reach up to 80.4 zero-shot top-1 on ImageNet-1K, outperforming the previous largest & best open-sourced CLIP with only ~1/6 parameters and ~1/6 image-text training data. We offer four EVA-02 variants in various model sizes, ranging from 6M to 304M parameters, all with impressive performance. To facilitate open access and open research, we release the complete suite of EVA-02 to the community at https://github.com/baaivision/EVA/tree/master/EVA-02.

Xinlong Wang, Xiaosong Zhang, Zhengxiong Luo et al. · tsinghua

While next-token prediction is considered a promising path towards artificial general intelligence, it has struggled to excel in multimodal tasks, which are still dominated by diffusion models (e.g., Stable Diffusion) and compositional approaches (e.g., CLIP combined with LLMs). In this paper, we introduce Emu3, a new suite of state-of-the-art multimodal models trained solely with next-token prediction. By tokenizing images, text, and videos into a discrete space, we train a single transformer from scratch on a mixture of multimodal sequences. Emu3 outperforms several well-established task-specific models in both generation and perception tasks, surpassing flagship models such as SDXL and LLaVA-1.6, while eliminating the need for diffusion or compositional architectures. Emu3 is also capable of generating high-fidelity video via predicting the next token in a video sequence. We simplify complex multimodal model designs by converging on a singular focus: tokens, unlocking great potential for scaling both during training and inference. Our results demonstrate that next-token prediction is a promising path towards building general multimodal intelligence beyond language. We open-source key techniques and models to support further research in this direction.

Wen Wang, Yan Jiang, Kangyang Xie et al.

Large-scale text-to-image diffusion models achieve unprecedented success in image generation and editing. However, how to extend such success to video editing is unclear. Recent initial attempts at video editing require significant text-to-video data and computation resources for training, which is often not accessible. In this work, we propose vid2vid-zero, a simple yet effective method for zero-shot video editing. Our vid2vid-zero leverages off-the-shelf image diffusion models, and doesn't require training on any video. At the core of our method is a null-text inversion module for text-to-video alignment, a cross-frame modeling module for temporal consistency, and a spatial regularization module for fidelity to the original video. Without any training, we leverage the dynamic nature of the attention mechanism to enable bi-directional temporal modeling at test time. Experiments and analyses show promising results in editing attributes, subjects, places, etc., in real-world videos. Code is made available at \url{https://github.com/baaivision/vid2vid-zero}.

Quan Sun, Qiying Yu, Yufeng Cui et al. · tsinghua

We present Emu, a Transformer-based multimodal foundation model, which can seamlessly generate images and texts in multimodal context. This omnivore model can take in any single-modality or multimodal data input indiscriminately (e.g., interleaved image, text and video) through a one-model-for-all autoregressive training process. First, visual signals are encoded into embeddings, and together with text tokens form an interleaved input sequence. Emu is then end-to-end trained with a unified objective of classifying the next text token or regressing the next visual embedding in the multimodal sequence. This versatile multimodality empowers the exploration of diverse pretraining data sources at scale, such as videos with interleaved frames and text, webpages with interleaved images and text, as well as web-scale image-text pairs and video-text pairs. Emu can serve as a generalist multimodal interface for both image-to-text and text-to-image tasks, and supports in-context image and text generation. Across a broad range of zero-shot/few-shot tasks including image captioning, visual question answering, video question answering and text-to-image generation, Emu demonstrates superb performance compared to state-of-the-art large multimodal models. Extended capabilities such as multimodal assistants via instruction tuning are also demonstrated with impressive performance.

Lingfeng Yang, Yueze Wang, Xiang Li et al.

Vision-Language Models (VLMs), such as CLIP, have demonstrated impressive zero-shot transfer capabilities in image-level visual perception. However, these models have shown limited performance in instance-level tasks that demand precise localization and recognition. Previous works have suggested that incorporating visual prompts, such as colorful boxes or circles, can improve the ability of models to recognize objects of interest. Nonetheless, compared to language prompting, visual prompting designs are rarely explored. Existing approaches, which employ coarse visual cues such as colorful boxes or circles, often result in sub-optimal performance due to the inclusion of irrelevant and noisy pixels. In this paper, we carefully study the visual prompting designs by exploring more fine-grained markings, such as segmentation masks and their variations. In addition, we introduce a new zero-shot framework that leverages pixel-level annotations acquired from a generalist segmentation model for fine-grained visual prompting. Consequently, our investigation reveals that a straightforward application of blur outside the target mask, referred to as the Blur Reverse Mask, exhibits exceptional effectiveness. This proposed prompting strategy leverages the precise mask annotations to reduce focus on weakly related regions while retaining spatial coherence between the target and the surrounding background. Our Fine-Grained Visual Prompting (FGVP) demonstrates superior performance in zero-shot comprehension of referring expressions on the RefCOCO, RefCOCO+, and RefCOCOg benchmarks. It outperforms prior methods by an average margin of 3.0% to 4.6%, with a maximum improvement of 12.5% on the RefCOCO+ testA subset. Code is available at https://github.com/ylingfeng/FGVP.

Xinlong Wang, Wen Wang, Yue Cao et al.

In-context learning, as a new paradigm in NLP, allows the model to rapidly adapt to various tasks with only a handful of prompts and examples. But in computer vision, the difficulties for in-context learning lie in that tasks vary significantly in the output representations, thus it is unclear how to define the general-purpose task prompts that the vision model can understand and transfer to out-of-domain tasks. In this work, we present Painter, a generalist model which addresses these obstacles with an "image"-centric solution, that is, to redefine the output of core vision tasks as images, and specify task prompts as also images. With this idea, our training process is extremely simple, which performs standard masked image modeling on the stitch of input and output image pairs. This makes the model capable of performing tasks conditioned on visible image patches. Thus, during inference, we can adopt a pair of input and output images from the same task as the input condition, to indicate which task to perform. Without bells and whistles, our generalist Painter can achieve competitive performance compared to well-established task-specific models, on seven representative vision tasks ranging from high-level visual understanding to low-level image processing. In addition, Painter significantly outperforms recent generalist models on several challenging tasks.

Xinlong Wang, Xiaosong Zhang, Yue Cao et al.

We present SegGPT, a generalist model for segmenting everything in context. We unify various segmentation tasks into a generalist in-context learning framework that accommodates different kinds of segmentation data by transforming them into the same format of images. The training of SegGPT is formulated as an in-context coloring problem with random color mapping for each data sample. The objective is to accomplish diverse tasks according to the context, rather than relying on specific colors. After training, SegGPT can perform arbitrary segmentation tasks in images or videos via in-context inference, such as object instance, stuff, part, contour, and text. SegGPT is evaluated on a broad range of tasks, including few-shot semantic segmentation, video object segmentation, semantic segmentation, and panoptic segmentation. Our results show strong capabilities in segmenting in-domain and out-of-domain targets, either qualitatively or quantitatively.

Lianghui Zhu, Xinggang Wang, Xinlong Wang

Evaluating Large Language Models (LLMs) in open-ended scenarios is challenging because existing benchmarks and metrics can not measure them comprehensively. To address this problem, we propose to fine-tune LLMs as scalable judges (JudgeLM) to evaluate LLMs efficiently and effectively in open-ended benchmarks. We first propose a comprehensive, large-scale, high-quality dataset containing task seeds, LLMs-generated answers, and GPT-4-generated judgments for fine-tuning high-performance judges, as well as a new benchmark for evaluating the judges. We train JudgeLM at different scales from 7B, 13B, to 33B parameters, and conduct a systematic analysis of its capabilities and behaviors. We then analyze the key biases in fine-tuning LLM as a judge and consider them as position bias, knowledge bias, and format bias. To address these issues, JudgeLM introduces a bag of techniques including swap augmentation, reference support, and reference drop, which clearly enhance the judge's performance. JudgeLM obtains the state-of-the-art judge performance on both the existing PandaLM benchmark and our proposed new benchmark. Our JudgeLM is efficient and the JudgeLM-7B only needs 3 minutes to judge 5K samples with 8 A100 GPUs. JudgeLM obtains high agreement with the teacher judge, achieving an agreement exceeding 90% that even surpasses human-to-human agreement. JudgeLM also demonstrates extended capabilities in being judges of the single answer, multimodal models, multiple answers, multi-turn chat, etc. Code is available at https://github.com/baaivision/JudgeLM.

Xiaotong Li, Fan Zhang, Haiwen Diao et al.

Existing Multimodal Large Language Models (MLLMs) increasingly emphasize complex understanding of various visual elements, including multiple objects, text information, and spatial relations. Their development for comprehensive visual perception hinges on the availability of high-quality image-text datasets that offer diverse visual elements and throughout image descriptions. However, the scarcity of such hyper-detailed datasets currently hinders progress within the MLLM community. The bottleneck stems from the limited perceptual capabilities of current caption engines, which fall short in providing complete and accurate annotations. To facilitate the cutting-edge research of MLLMs on comprehensive vision perception, we thereby propose Perceptual Fusion, using a low-budget but highly effective caption engine for complete and accurate image descriptions. Specifically, Perceptual Fusion integrates diverse perception experts as image priors to provide explicit information on visual elements and adopts an efficient MLLM as a centric pivot to mimic advanced MLLMs' perception abilities. We carefully select 1M highly representative images from uncurated LAION dataset and generate dense descriptions using our engine, dubbed DenseFusion-1M. Extensive experiments validate that our engine outperforms its counterparts, where the resulting dataset significantly improves the perception and cognition abilities of existing MLLMs across diverse vision-language benchmarks, especially with high-resolution images as inputs. The dataset and code are publicly available at https://github.com/baaivision/DenseFusion.

Yongtao Ge, Qiang Zhou, Xinlong Wang et al.

Point annotations are considerably more time-efficient than bounding box annotations. However, how to use cheap point annotations to boost the performance of semi-supervised object detection remains largely unsolved. In this work, we present Point-Teaching, a weakly semi-supervised object detection framework to fully exploit the point annotations. Specifically, we propose a Hungarian-based point matching method to generate pseudo labels for point annotated images. We further propose multiple instance learning (MIL) approaches at the level of images and points to supervise the object detector with point annotations. Finally, we propose a simple-yet-effective data augmentation, termed point-guided copy-paste, to reduce the impact of the unmatched points. Experiments demonstrate the effectiveness of our method on a few datasets and various data regimes.

Chunyi Sun, Junlin Han, Weijian Deng et al. · oxford

In the pursuit of efficient automated content creation, procedural generation, leveraging modifiable parameters and rule-based systems, emerges as a promising approach. Nonetheless, it could be a demanding endeavor, given its intricate nature necessitating a deep understanding of rules, algorithms, and parameters. To reduce workload, we introduce 3D-GPT, a framework utilizing large language models~(LLMs) for instruction-driven 3D modeling. 3D-GPT positions LLMs as proficient problem solvers, dissecting the procedural 3D modeling tasks into accessible segments and appointing the apt agent for each task. 3D-GPT integrates three core agents: the task dispatch agent, the conceptualization agent, and the modeling agent. They collaboratively achieve two objectives. First, it enhances concise initial scene descriptions, evolving them into detailed forms while dynamically adapting the text based on subsequent instructions. Second, it integrates procedural generation, extracting parameter values from enriched text to effortlessly interface with 3D software for asset creation. Our empirical investigations confirm that 3D-GPT not only interprets and executes instructions, delivering reliable results but also collaborates effectively with human designers. Furthermore, it seamlessly integrates with Blender, unlocking expanded manipulation possibilities. Our work highlights the potential of LLMs in 3D modeling, offering a basic framework for future advancements in scene generation and animation.

Qiying Yu, Quan Sun, Xiaosong Zhang et al. · tsinghua

Large multimodal models demonstrate remarkable generalist ability to perform diverse multimodal tasks in a zero-shot manner. Large-scale web-based image-text pairs contribute fundamentally to this success, but suffer from excessive noise. Recent studies use alternative captions synthesized by captioning models and have achieved notable benchmark performance. However, our experiments reveal significant Scalability Deficiency and World Knowledge Loss issues in models trained with synthetic captions, which have been largely obscured by their initial benchmark success. Upon closer examination, we identify the root cause as the overly-simplified language structure and lack of knowledge details in existing synthetic captions. To provide higher-quality and more scalable multimodal pretraining data, we propose CapsFusion, an advanced framework that leverages large language models to consolidate and refine information from both web-based image-text pairs and synthetic captions. Extensive experiments show that CapsFusion captions exhibit remarkable all-round superiority over existing captions in terms of model performance (e.g., 18.8 and 18.3 improvements in CIDEr score on COCO and NoCaps), sample efficiency (requiring 11-16 times less computation than baselines), world knowledge depth, and scalability. These effectiveness, efficiency and scalability advantages position CapsFusion as a promising candidate for future scaling of LMM training.

Junsheng Zhou, Jinsheng Wang, Baorui Ma et al.

Scaling up representations for images or text has been extensively investigated in the past few years and has led to revolutions in learning vision and language. However, scalable representation for 3D objects and scenes is relatively unexplored. In this work, we present Uni3D, a 3D foundation model to explore the unified 3D representation at scale. Uni3D uses a 2D initialized ViT end-to-end pretrained to align the 3D point cloud features with the image-text aligned features. Via the simple architecture and pretext task, Uni3D can leverage abundant 2D pretrained models as initialization and image-text aligned models as the target, unlocking the great potential of 2D models and scaling-up strategies to the 3D world. We efficiently scale up Uni3D to one billion parameters, and set new records on a broad range of 3D tasks, such as zero-shot classification, few-shot classification, open-world understanding and part segmentation. We show that the strong Uni3D representation also enables applications such as 3D painting and retrieval in the wild. We believe that Uni3D provides a new direction for exploring both scaling up and efficiency of the representation in 3D domain.

Lianghui Zhu, Bencheng Liao, Qian Zhang et al.

Recently the state space models (SSMs) with efficient hardware-aware designs, i.e., the Mamba deep learning model, have shown great potential for long sequence modeling. Meanwhile building efficient and generic vision backbones purely upon SSMs is an appealing direction. However, representing visual data is challenging for SSMs due to the position-sensitivity of visual data and the requirement of global context for visual understanding. In this paper, we show that the reliance on self-attention for visual representation learning is not necessary and propose a new generic vision backbone with bidirectional Mamba blocks (Vim), which marks the image sequences with position embeddings and compresses the visual representation with bidirectional state space models. On ImageNet classification, COCO object detection, and ADE20k semantic segmentation tasks, Vim achieves higher performance compared to well-established vision transformers like DeiT, while also demonstrating significantly improved computation & memory efficiency. For example, Vim is 2.8$\times$ faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on images with a resolution of 1248$\times$1248. The results demonstrate that Vim is capable of overcoming the computation & memory constraints on performing Transformer-style understanding for high-resolution images and it has great potential to be the next-generation backbone for vision foundation models. Code is available at https://github.com/hustvl/Vim.

Baorui Ma, Haoge Deng, Junsheng Zhou et al.

Text-to-3D generation by distilling pretrained large-scale text-to-image diffusion models has shown great promise but still suffers from inconsistent 3D geometric structures (Janus problems) and severe artifacts. The aforementioned problems mainly stem from 2D diffusion models lacking 3D awareness during the lifting. In this work, we present GeoDream, a novel method that incorporates explicit generalized 3D priors with 2D diffusion priors to enhance the capability of obtaining unambiguous 3D consistent geometric structures without sacrificing diversity or fidelity. Specifically, we first utilize a multi-view diffusion model to generate posed images and then construct cost volume from the predicted image, which serves as native 3D geometric priors, ensuring spatial consistency in 3D space. Subsequently, we further propose to harness 3D geometric priors to unlock the great potential of 3D awareness in 2D diffusion priors via a disentangled design. Notably, disentangling 2D and 3D priors allows us to refine 3D geometric priors further. We justify that the refined 3D geometric priors aid in the 3D-aware capability of 2D diffusion priors, which in turn provides superior guidance for the refinement of 3D geometric priors. Our numerical and visual comparisons demonstrate that GeoDream generates more 3D consistent textured meshes with high-resolution realistic renderings (i.e., 1024 $\times$ 1024) and adheres more closely to semantic coherence.

Haoge Deng, Ting Pan, Haiwen Diao et al.

This paper presents a novel approach that enables autoregressive video generation with high efficiency. We propose to reformulate the video generation problem as a non-quantized autoregressive modeling of temporal frame-by-frame prediction and spatial set-by-set prediction. Unlike raster-scan prediction in prior autoregressive models or joint distribution modeling of fixed-length tokens in diffusion models, our approach maintains the causal property of GPT-style models for flexible in-context capabilities, while leveraging bidirectional modeling within individual frames for efficiency. With the proposed approach, we train a novel video autoregressive model without vector quantization, termed NOVA. Our results demonstrate that NOVA surpasses prior autoregressive video models in data efficiency, inference speed, visual fidelity, and video fluency, even with a much smaller model capacity, i.e., 0.6B parameters. NOVA also outperforms state-of-the-art image diffusion models in text-to-image generation tasks, with a significantly lower training cost. Additionally, NOVA generalizes well across extended video durations and enables diverse zero-shot applications in one unified model. Code and models are publicly available at https://github.com/baaivision/NOVA.

Ting Pan, Lulu Tang, Xinlong Wang et al.

We present a unified, promptable model capable of simultaneously segmenting, recognizing, and captioning anything. Unlike SAM, we aim to build a versatile region representation in the wild via visual prompting. To achieve this, we train a generalizable model with massive segmentation masks, \eg, SA-1B masks, and semantic priors from a pre-trained CLIP model with 5 billion parameters. Specifically, we construct a promptable image decoder by adding a semantic token to each mask token. The semantic token is responsible for learning the semantic priors in a predefined concept space. Through joint optimization of segmentation on mask tokens and concept prediction on semantic tokens, our model exhibits strong regional recognition and localization capabilities. For example, an additional 38M-parameter causal text decoder trained from scratch sets a new record with a CIDEr score of 164.7 on the Visual Genome region captioning task. We believe this model can be a versatile region-level image tokenizer, capable of encoding general-purpose region context for a broad range of visual perception tasks. Code and models are available at {\footnotesize \url{https://github.com/baaivision/tokenize-anything}}.

Quan Sun, Yufeng Cui, Xiaosong Zhang et al. · tsinghua

The human ability to easily solve multimodal tasks in context (i.e., with only a few demonstrations or simple instructions), is what current multimodal systems have largely struggled to imitate. In this work, we demonstrate that the task-agnostic in-context learning capabilities of large multimodal models can be significantly enhanced by effective scaling-up. We introduce Emu2, a generative multimodal model with 37 billion parameters, trained on large-scale multimodal sequences with a unified autoregressive objective. Emu2 exhibits strong multimodal in-context learning abilities, even emerging to solve tasks that require on-the-fly reasoning, such as visual prompting and object-grounded generation. The model sets a new record on multiple multimodal understanding tasks in few-shot settings. When instruction-tuned to follow specific instructions, Emu2 further achieves new state-of-the-art on challenging tasks such as question answering benchmarks for large multimodal models and open-ended subject-driven generation. These achievements demonstrate that Emu2 can serve as a base model and general-purpose interface for a wide range of multimodal tasks. Code and models are publicly available to facilitate future research.

Yang Liu, Muzhi Zhu, Hengtao Li et al.

Powered by large-scale pre-training, vision foundation models exhibit significant potential in open-world image understanding. However, unlike large language models that excel at directly tackling various language tasks, vision foundation models require a task-specific model structure followed by fine-tuning on specific tasks. In this work, we present Matcher, a novel perception paradigm that utilizes off-the-shelf vision foundation models to address various perception tasks. Matcher can segment anything by using an in-context example without training. Additionally, we design three effective components within the Matcher framework to collaborate with these foundation models and unleash their full potential in diverse perception tasks. Matcher demonstrates impressive generalization performance across various segmentation tasks, all without training. For example, it achieves 52.7% mIoU on COCO-20$^i$ with one example, surpassing the state-of-the-art specialist model by 1.6%. In addition, Matcher achieves 33.0% mIoU on the proposed LVIS-92$^i$ for one-shot semantic segmentation, outperforming the state-of-the-art generalist model by 14.4%. Our visualization results further showcase the open-world generality and flexibility of Matcher when applied to images in the wild. Our code can be found at https://github.com/aim-uofa/Matcher.

Xinlong Wang, Zhiding Yu, Shalini De Mello et al.

Instance segmentation is a fundamental vision task that aims to recognize and segment each object in an image. However, it requires costly annotations such as bounding boxes and segmentation masks for learning. In this work, we propose a fully unsupervised learning method that learns class-agnostic instance segmentation without any annotations. We present FreeSOLO, a self-supervised instance segmentation framework built on top of the simple instance segmentation method SOLO. Our method also presents a novel localization-aware pre-training framework, where objects can be discovered from complicated scenes in an unsupervised manner. FreeSOLO achieves 9.8% AP_{50} on the challenging COCO dataset, which even outperforms several segmentation proposal methods that use manual annotations. For the first time, we demonstrate unsupervised class-agnostic instance segmentation successfully. FreeSOLO's box localization significantly outperforms state-of-the-art unsupervised object detection/discovery methods, with about 100% relative improvements in COCO AP. FreeSOLO further demonstrates superiority as a strong pre-training method, outperforming state-of-the-art self-supervised pre-training methods by +9.8% AP when fine-tuning instance segmentation with only 5% COCO masks. Code is available at: github.com/NVlabs/FreeSOLO

Xinlong Wang, Rufeng Zhang, Chunhua Shen et al.

Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that has made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-then-segment' strategy (e.g., Mask R-CNN), or predict embedding vectors first then cluster pixels into individual instances. In this paper, we view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location. With this notion, we propose segmenting objects by locations (SOLO), a simple, direct, and fast framework for instance segmentation with strong performance. We derive a few SOLO variants (e.g., Vanilla SOLO, Decoupled SOLO, Dynamic SOLO) following the basic principle. Our method directly maps a raw input image to the desired object categories and instance masks, eliminating the need for the grouping post-processing or the bounding box detection. Our approach achieves state-of-the-art results for instance segmentation in terms of both speed and accuracy, while being considerably simpler than the existing methods. Besides instance segmentation, our method yields state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation. We further demonstrate the flexibility and high-quality segmentation of SOLO by extending it to perform one-stage instance-level image matting. Code is available at: https://git.io/AdelaiDet

Weian Mao, Zhi Tian, Xinlong Wang et al.

We propose a fully convolutional multi-person pose estimation framework using dynamic instance-aware convolutions, termed FCPose. Different from existing methods, which often require ROI (Region of Interest) operations and/or grouping post-processing, FCPose eliminates the ROIs and grouping post-processing with dynamic instance-aware keypoint estimation heads. The dynamic keypoint heads are conditioned on each instance (person), and can encode the instance concept in the dynamically-generated weights of their filters. Moreover, with the strong representation capacity of dynamic convolutions, the keypoint heads in FCPose are designed to be very compact, resulting in fast inference and making FCPose have almost constant inference time regardless of the number of persons in the image. For example, on the COCO dataset, a real-time version of FCPose using the DLA-34 backbone infers about 4.5x faster than Mask R-CNN (ResNet-101) (41.67 FPS vs. 9.26FPS) while achieving improved performance. FCPose also offers better speed/accuracy trade-off than other state-of-the-art methods. Our experiment results show that FCPose is a simple yet effective multi-person pose estimation framework. Code is available at: https://git.io/AdelaiDet

Xiangxiang Chu, Zhi Tian, Bo Zhang et al.

We propose a conditional positional encoding (CPE) scheme for vision Transformers. Unlike previous fixed or learnable positional encodings, which are pre-defined and independent of input tokens, CPE is dynamically generated and conditioned on the local neighborhood of the input tokens. As a result, CPE can easily generalize to the input sequences that are longer than what the model has ever seen during training. Besides, CPE can keep the desired translation-invariance in the image classification task, resulting in improved performance. We implement CPE with a simple Position Encoding Generator (PEG) to get seamlessly incorporated into the current Transformer framework. Built on PEG, we present Conditional Position encoding Vision Transformer (CPVT). We demonstrate that CPVT has visually similar attention maps compared to those with learned positional encodings and delivers outperforming results. Our code is available at https://github.com/Meituan-AutoML/CPVT .

Xinyu Zhang, Xinlong Wang, Jia-Wang Bian et al.

Person search aims to localize and identify a specific person from a gallery of images. Recent methods can be categorized into two groups, i.e., two-step and end-to-end approaches. The former views person search as two independent tasks and achieves dominant results using separately trained person detection and re-identification (Re-ID) models. The latter performs person search in an end-to-end fashion. Although the end-to-end approaches yield higher inference efficiency, they largely lag behind those two-step counterparts in terms of accuracy. In this paper, we argue that the gap between the two kinds of methods is mainly caused by the Re-ID sub-networks of end-to-end methods. To this end, we propose a simple yet strong end-to-end network with diverse knowledge distillation to break the bottleneck. We also design a spatial-invariant augmentation to assist model to be invariant to inaccurate detection results. Experimental results on the CUHK-SYSU and PRW datasets demonstrate the superiority of our method against existing approaches -- it achieves on par accuracy with state-of-the-art two-step methods while maintaining high efficiency due to the single joint model. Code is available at: https://git.io/DKD-PersonSearch.

Zhi Tian, Chunhua Shen, Xinlong Wang et al.

We present a high-performance method that can achieve mask-level instance segmentation with only bounding-box annotations for training. While this setting has been studied in the literature, here we show significantly stronger performance with a simple design (e.g., dramatically improving previous best reported mask AP of 21.1% in Hsu et al. (2019) to 31.6% on the COCO dataset). Our core idea is to redesign the loss of learning masks in instance segmentation, with no modification to the segmentation network itself. The new loss functions can supervise the mask training without relying on mask annotations. This is made possible with two loss terms, namely, 1) a surrogate term that minimizes the discrepancy between the projections of the ground-truth box and the predicted mask; 2) a pairwise loss that can exploit the prior that proximal pixels with similar colors are very likely to have the same category label. Experiments demonstrate that the redesigned mask loss can yield surprisingly high-quality instance masks with only box annotations. For example, without using any mask annotations, with a ResNet-101 backbone and 3x training schedule, we achieve 33.2% mask AP on COCO test-dev split (vs. 39.1% of the fully supervised counterpart). Our excellent experiment results on COCO and Pascal VOC indicate that our method dramatically narrows the performance gap between weakly and fully supervised instance segmentation. Code is available at: https://git.io/AdelaiDet

Xinlong Wang, Rufeng Zhang, Chunhua Shen et al.

To date, most existing self-supervised learning methods are designed and optimized for image classification. These pre-trained models can be sub-optimal for dense prediction tasks due to the discrepancy between image-level prediction and pixel-level prediction. To fill this gap, we aim to design an effective, dense self-supervised learning method that directly works at the level of pixels (or local features) by taking into account the correspondence between local features. We present dense contrastive learning, which implements self-supervised learning by optimizing a pairwise contrastive (dis)similarity loss at the pixel level between two views of input images. Compared to the baseline method MoCo-v2, our method introduces negligible computation overhead (only <1% slower), but demonstrates consistently superior performance when transferring to downstream dense prediction tasks including object detection, semantic segmentation and instance segmentation; and outperforms the state-of-the-art methods by a large margin. Specifically, over the strong MoCo-v2 baseline, our method achieves significant improvements of 2.0% AP on PASCAL VOC object detection, 1.1% AP on COCO object detection, 0.9% AP on COCO instance segmentation, 3.0% mIoU on PASCAL VOC semantic segmentation and 1.8% mIoU on Cityscapes semantic segmentation. Code is available at: https://git.io/AdelaiDet

Xinlong Wang, Rufeng Zhang, Tao Kong et al.

In this work, we aim at building a simple, direct, and fast instance segmentation framework with strong performance. We follow the principle of the SOLO method of Wang et al. "SOLO: segmenting objects by locations". Importantly, we take one step further by dynamically learning the mask head of the object segmenter such that the mask head is conditioned on the location. Specifically, the mask branch is decoupled into a mask kernel branch and mask feature branch, which are responsible for learning the convolution kernel and the convolved features respectively. Moreover, we propose Matrix NMS (non maximum suppression) to significantly reduce the inference time overhead due to NMS of masks. Our Matrix NMS performs NMS with parallel matrix operations in one shot, and yields better results. We demonstrate a simple direct instance segmentation system, outperforming a few state-of-the-art methods in both speed and accuracy. A light-weight version of SOLOv2 executes at 31.3 FPS and yields 37.1% AP. Moreover, our state-of-the-art results in object detection (from our mask byproduct) and panoptic segmentation show the potential to serve as a new strong baseline for many instance-level recognition tasks besides instance segmentation. Code is available at: https://git.io/AdelaiDet

Xinlong Wang, Wei Yin, Tao Kong et al.

Monocular depth estimation enables 3D perception from a single 2D image, thus attracting much research attention for years. Almost all methods treat foreground and background regions ("things and stuff") in an image equally. However, not all pixels are equal. Depth of foreground objects plays a crucial role in 3D object recognition and localization. To date how to boost the depth prediction accuracy of foreground objects is rarely discussed. In this paper, we first analyse the data distributions and interaction of foreground and background, then propose the foreground-background separated monocular depth estimation (ForeSeE) method, to estimate the foreground depth and background depth using separate optimization objectives and depth decoders. Our method significantly improves the depth estimation performance on foreground objects. Applying ForeSeE to 3D object detection, we achieve 7.5 AP gains and set new state-of-the-art results among other monocular methods. Code will be available at: https://github.com/WXinlong/ForeSeE.

Xinlong Wang, Shu Liu, Xiaoyong Shen et al.

A 3D point cloud describes the real scene precisely and intuitively.To date how to segment diversified elements in such an informative 3D scene is rarely discussed. In this paper, we first introduce a simple and flexible framework to segment instances and semantics in point clouds simultaneously. Then, we propose two approaches which make the two tasks take advantage of each other, leading to a win-win situation. Specifically, we make instance segmentation benefit from semantic segmentation through learning semantic-aware point-level instance embedding. Meanwhile, semantic features of the points belonging to the same instance are fused together to make more accurate per-point semantic predictions. Our method largely outperforms the state-of-the-art method in 3D instance segmentation along with a significant improvement in 3D semantic segmentation. Code has been made available at: https://github.com/WXinlong/ASIS.

Baorui Ma, Huachen Gao, Haoge Deng et al.

Recent 3D generation models typically rely on limited-scale 3D `gold-labels' or 2D diffusion priors for 3D content creation. However, their performance is upper-bounded by constrained 3D priors due to the lack of scalable learning paradigms. In this work, we present See3D, a visual-conditional multi-view diffusion model trained on large-scale Internet videos for open-world 3D creation. The model aims to Get 3D knowledge by solely Seeing the visual contents from the vast and rapidly growing video data -- You See it, You Got it. To achieve this, we first scale up the training data using a proposed data curation pipeline that automatically filters out multi-view inconsistencies and insufficient observations from source videos. This results in a high-quality, richly diverse, large-scale dataset of multi-view images, termed WebVi3D, containing 320M frames from 16M video clips. Nevertheless, learning generic 3D priors from videos without explicit 3D geometry or camera pose annotations is nontrivial, and annotating poses for web-scale videos is prohibitively expensive. To eliminate the need for pose conditions, we introduce an innovative visual-condition - a purely 2D-inductive visual signal generated by adding time-dependent noise to the masked video data. Finally, we introduce a novel visual-conditional 3D generation framework by integrating See3D into a warping-based pipeline for high-fidelity 3D generation. Our numerical and visual comparisons on single and sparse reconstruction benchmarks show that See3D, trained on cost-effective and scalable video data, achieves notable zero-shot and open-world generation capabilities, markedly outperforming models trained on costly and constrained 3D datasets. Please refer to our project page at: https://vision.baai.ac.cn/see3d

Wenxuan Wang, Fan Zhang, Yufeng Cui et al.

Existing vision tokenization isolates the optimization of vision tokenizers from downstream training, implicitly assuming the visual tokens can generalize well across various tasks, e.g., image generation and visual question answering. The vision tokenizer optimized for low-level reconstruction is agnostic to downstream tasks requiring varied representations and semantics. This decoupled paradigm introduces a critical misalignment: The loss of the vision tokenization can be the representation bottleneck for target tasks. For example, errors in tokenizing text in a given image lead to poor results when recognizing or generating them. To address this, we propose ETT, an end-to-end vision tokenizer tuning approach that enables joint optimization between vision tokenization and target autoregressive tasks. Unlike prior autoregressive models that use only discrete indices from a frozen vision tokenizer, ETT leverages the visual embeddings of the tokenizer codebook, and optimizes the vision tokenizers end-to-end with both reconstruction and caption objectives. ETT can be seamlessly integrated into existing training pipelines with minimal architecture modifications. Our ETT is simple to implement and integrate, without the need to adjust the original codebooks or architectures of the employed large language models. Extensive experiments demonstrate that our proposed end-to-end vision tokenizer tuning unlocks significant performance gains, i.e., 2-6% for multimodal understanding and visual generation tasks compared to frozen tokenizer baselines, while preserving the original reconstruction capability. We hope this very simple and strong method can empower multimodal foundation models besides image generation and understanding.

Yi Liu, Yuan Tian, Jianxun Lian et al.

Dense retrieval is widely used for entity linking to retrieve entities from large-scale knowledge bases. Mainstream techniques are based on a dual-encoder framework, which encodes mentions and entities independently and calculates their relevances via rough interaction metrics, resulting in difficulty in explicitly modeling multiple mention-relevant parts within entities to match divergent mentions. Aiming at learning entity representations that can match divergent mentions, this paper proposes a Multi-View Enhanced Distillation (MVD) framework, which can effectively transfer knowledge of multiple fine-grained and mention-relevant parts within entities from cross-encoders to dual-encoders. Each entity is split into multiple views to avoid irrelevant information being over-squashed into the mention-relevant view. We further design cross-alignment and self-alignment mechanisms for this framework to facilitate fine-grained knowledge distillation from the teacher model to the student model. Meanwhile, we reserve a global-view that embeds the entity as a whole to prevent dispersal of uniform information. Experiments show our method achieves state-of-the-art performance on several entity linking benchmarks.

Weian Mao, Yongtao Ge, Chunhua Shen et al.

We propose a direct, regression-based approach to 2D human pose estimation from single images. We formulate the problem as a sequence prediction task, which we solve using a Transformer network. This network directly learns a regression mapping from images to the keypoint coordinates, without resorting to intermediate representations such as heatmaps. This approach avoids much of the complexity associated with heatmap-based approaches. To overcome the feature misalignment issues of previous regression-based methods, we propose an attention mechanism that adaptively attends to the features that are most relevant to the target keypoints, considerably improving the accuracy. Importantly, our framework is end-to-end differentiable, and naturally learns to exploit the dependencies between keypoints. Experiments on MS-COCO and MPII, two predominant pose-estimation datasets, demonstrate that our method significantly improves upon the state-of-the-art in regression-based pose estimation. More notably, ours is the first regression-based approach to perform favorably compared to the best heatmap-based pose estimation methods.

Weian Mao, Yongtao Ge, Chunhua Shen et al.

We propose a human pose estimation framework that solves the task in the regression-based fashion. Unlike previous regression-based methods, which often fall behind those state-of-the-art methods, we formulate the pose estimation task into a sequence prediction problem that can effectively be solved by transformers. Our framework is simple and direct, bypassing the drawbacks of the heatmap-based pose estimation. Moreover, with the attention mechanism in transformers, our proposed framework is able to adaptively attend to the features most relevant to the target keypoints, which largely overcomes the feature misalignment issue of previous regression-based methods and considerably improves the performance. Importantly, our framework can inherently take advantages of the structured relationship between keypoints. Experiments on the MS-COCO and MPII datasets demonstrate that our method can significantly improve the state-of-the-art of regression-based pose estimation and perform comparably with the best heatmap-based pose estimation methods.

Yuqing Wang, Zhaoliang Xu, Xinlong Wang et al.

Video instance segmentation (VIS) is the task that requires simultaneously classifying, segmenting and tracking object instances of interest in video. Recent methods typically develop sophisticated pipelines to tackle this task. Here, we propose a new video instance segmentation framework built upon Transformers, termed VisTR, which views the VIS task as a direct end-to-end parallel sequence decoding/prediction problem. Given a video clip consisting of multiple image frames as input, VisTR outputs the sequence of masks for each instance in the video in order directly. At the core is a new, effective instance sequence matching and segmentation strategy, which supervises and segments instances at the sequence level as a whole. VisTR frames the instance segmentation and tracking in the same perspective of similarity learning, thus considerably simplifying the overall pipeline and is significantly different from existing approaches. Without bells and whistles, VisTR achieves the highest speed among all existing VIS models, and achieves the best result among methods using single model on the YouTube-VIS dataset. For the first time, we demonstrate a much simpler and faster video instance segmentation framework built upon Transformers, achieving competitive accuracy. We hope that VisTR can motivate future research for more video understanding tasks.

Wei Yin, Xinlong Wang, Chunhua Shen et al.

We present a method for depth estimation with monocular images, which can predict high-quality depth on diverse scenes up to an affine transformation, thus preserving accurate shapes of a scene. Previous methods that predict metric depth often work well only for a specific scene. In contrast, learning relative depth (information of being closer or further) can enjoy better generalization, with the price of failing to recover the accurate geometric shape of the scene. In this work, we propose a dataset and methods to tackle this dilemma, aiming to predict accurate depth up to an affine transformation with good generalization to diverse scenes. First we construct a large-scale and diverse dataset, termed Diverse Scene Depth dataset (DiverseDepth), which has a broad range of scenes and foreground contents. Compared with previous learning objectives, i.e., learning metric depth or relative depth, we propose to learn the affine-invariant depth using our diverse dataset to ensure both generalization and high-quality geometric shapes of scenes. Furthermore, in order to train the model on the complex dataset effectively, we propose a multi-curriculum learning method. Experiments show that our method outperforms previous methods on 8 datasets by a large margin with the zero-shot test setting, demonstrating the excellent generalization capacity of the learned model to diverse scenes. The reconstructed point clouds with the predicted depth show that our method can recover high-quality 3D shapes. Code and dataset are available at: https://tinyurl.com/DiverseDepth

Xinlong Wang, Tao Kong, Chunhua Shen et al.

We present a new, embarrassingly simple approach to instance segmentation in images. Compared to many other dense prediction tasks, e.g., semantic segmentation, it is the arbitrary number of instances that have made instance segmentation much more challenging. In order to predict a mask for each instance, mainstream approaches either follow the 'detect-thensegment' strategy as used by Mask R-CNN, or predict category masks first then use clustering techniques to group pixels into individual instances. We view the task of instance segmentation from a completely new perspective by introducing the notion of "instance categories", which assigns categories to each pixel within an instance according to the instance's location and size, thus nicely converting instance mask segmentation into a classification-solvable problem. Now instance segmentation is decomposed into two classification tasks. We demonstrate a much simpler and flexible instance segmentation framework with strong performance, achieving on par accuracy with Mask R-CNN and outperforming recent singleshot instance segmenters in accuracy. We hope that this very simple and strong framework can serve as a baseline for many instance-level recognition tasks besides instance segmentation.

Xinlong Wang, Tete Xiao, Yuning Jiang et al.

Detecting individual pedestrians in a crowd remains a challenging problem since the pedestrians often gather together and occlude each other in real-world scenarios. In this paper, we first explore how a state-of-the-art pedestrian detector is harmed by crowd occlusion via experimentation, providing insights into the crowd occlusion problem. Then, we propose a novel bounding box regression loss specifically designed for crowd scenes, termed repulsion loss. This loss is driven by two motivations: the attraction by target, and the repulsion by other surrounding objects. The repulsion term prevents the proposal from shifting to surrounding objects thus leading to more crowd-robust localization. Our detector trained by repulsion loss outperforms all the state-of-the-art methods with a significant improvement in occlusion cases.

Xinlong Wang, Zhipeng Man, Mingyu You et al.

Generative Adversarial Networks (GAN) have attracted much research attention recently, leading to impressive results for natural image generation. However, to date little success was observed in using GAN generated images for improving classification tasks. Here we attempt to explore, in the context of car license plate recognition, whether it is possible to generate synthetic training data using GAN to improve recognition accuracy. With a carefully-designed pipeline, we show that the answer is affirmative. First, a large-scale image set is generated using the generator of GAN, without manual annotation. Then, these images are fed to a deep convolutional neural network (DCNN) followed by a bidirectional recurrent neural network (BRNN) with long short-term memory (LSTM), which performs the feature learning and sequence labelling. Finally, the pre-trained model is fine-tuned on real images. Our experimental results on a few data sets demonstrate the effectiveness of using GAN images: an improvement of 7.5% over a strong baseline with moderate-sized real data being available. We show that the proposed framework achieves competitive recognition accuracy on challenging test datasets. We also leverage the depthwise separate convolution to construct a lightweight convolutional RNN, which is about half size and 2x faster on CPU. Combining this framework and the proposed pipeline, we make progress in performing accurate recognition on mobile and embedded devices.