Jiaya Jia

Xin Lai, Zhuotao Tian, Yukang Chen et al.

Although perception systems have made remarkable advancements in recent years, they still rely on explicit human instruction or pre-defined categories to identify the target objects before executing visual recognition tasks. Such systems cannot actively reason and comprehend implicit user intention. In this work, we propose a new segmentation task -- reasoning segmentation. The task is designed to output a segmentation mask given a complex and implicit query text. Furthermore, we establish a benchmark comprising over one thousand image-instruction-mask data samples, incorporating intricate reasoning and world knowledge for evaluation purposes. Finally, we present LISA: large Language Instructed Segmentation Assistant, which inherits the language generation capabilities of multimodal Large Language Models (LLMs) while also possessing the ability to produce segmentation masks. We expand the original vocabulary with a <SEG> token and propose the embedding-as-mask paradigm to unlock the segmentation capability. Remarkably, LISA can handle cases involving complex reasoning and world knowledge. Also, it demonstrates robust zero-shot capability when trained exclusively on reasoning-free datasets. In addition, fine-tuning the model with merely 239 reasoning segmentation data samples results in further performance enhancement. Both quantitative and qualitative experiments show our method effectively unlocks new reasoning segmentation capabilities for multimodal LLMs. Code, models, and data are available at https://github.com/dvlab-research/LISA.

Wenbo Li, Zhe Lin, Kun Zhou et al.

Recent studies have shown the importance of modeling long-range interactions in the inpainting problem. To achieve this goal, existing approaches exploit either standalone attention techniques or transformers, but usually under a low resolution in consideration of computational cost. In this paper, we present a novel transformer-based model for large hole inpainting, which unifies the merits of transformers and convolutions to efficiently process high-resolution images. We carefully design each component of our framework to guarantee the high fidelity and diversity of recovered images. Specifically, we customize an inpainting-oriented transformer block, where the attention module aggregates non-local information only from partial valid tokens, indicated by a dynamic mask. Extensive experiments demonstrate the state-of-the-art performance of the new model on multiple benchmark datasets. Code is released at https://github.com/fenglinglwb/MAT.

Xin Lai, Jianhui Liu, Li Jiang et al.

3D point cloud segmentation has made tremendous progress in recent years. Most current methods focus on aggregating local features, but fail to directly model long-range dependencies. In this paper, we propose Stratified Transformer that is able to capture long-range contexts and demonstrates strong generalization ability and high performance. Specifically, we first put forward a novel key sampling strategy. For each query point, we sample nearby points densely and distant points sparsely as its keys in a stratified way, which enables the model to enlarge the effective receptive field and enjoy long-range contexts at a low computational cost. Also, to combat the challenges posed by irregular point arrangements, we propose first-layer point embedding to aggregate local information, which facilitates convergence and boosts performance. Besides, we adopt contextual relative position encoding to adaptively capture position information. Finally, a memory-efficient implementation is introduced to overcome the issue of varying point numbers in each window. Extensive experiments demonstrate the effectiveness and superiority of our method on S3DIS, ScanNetv2 and ShapeNetPart datasets. Code is available at https://github.com/dvlab-research/Stratified-Transformer.

Yanwei Li, Yilun Chen, Xiaojuan Qi et al.

In this work, we present a unified framework for multi-modality 3D object detection, named UVTR. The proposed method aims to unify multi-modality representations in the voxel space for accurate and robust single- or cross-modality 3D detection. To this end, the modality-specific space is first designed to represent different inputs in the voxel feature space. Different from previous work, our approach preserves the voxel space without height compression to alleviate semantic ambiguity and enable spatial connections. To make full use of the inputs from different sensors, the cross-modality interaction is then proposed, including knowledge transfer and modality fusion. In this way, geometry-aware expressions in point clouds and context-rich features in images are well utilized for better performance and robustness. The transformer decoder is applied to efficiently sample features from the unified space with learnable positions, which facilitates object-level interactions. In general, UVTR presents an early attempt to represent different modalities in a unified framework. It surpasses previous work in single- or multi-modality entries. The proposed method achieves leading performance in the nuScenes test set for both object detection and the following object tracking task. Code is made publicly available at https://github.com/dvlab-research/UVTR.

Yukang Chen, Yanwei Li, Xiangyu Zhang et al.

Non-uniformed 3D sparse data, e.g., point clouds or voxels in different spatial positions, make contribution to the task of 3D object detection in different ways. Existing basic components in sparse convolutional networks (Sparse CNNs) process all sparse data, regardless of regular or submanifold sparse convolution. In this paper, we introduce two new modules to enhance the capability of Sparse CNNs, both are based on making feature sparsity learnable with position-wise importance prediction. They are focal sparse convolution (Focals Conv) and its multi-modal variant of focal sparse convolution with fusion, or Focals Conv-F for short. The new modules can readily substitute their plain counterparts in existing Sparse CNNs and be jointly trained in an end-to-end fashion. For the first time, we show that spatially learnable sparsity in sparse convolution is essential for sophisticated 3D object detection. Extensive experiments on the KITTI, nuScenes and Waymo benchmarks validate the effectiveness of our approach. Without bells and whistles, our results outperform all existing single-model entries on the nuScenes test benchmark at the paper submission time. Code and models are at https://github.com/dvlab-research/FocalsConv.

Xin Lai, Yukang Chen, Fanbin Lu et al.

LiDAR-based 3D point cloud recognition has benefited various applications. Without specially considering the LiDAR point distribution, most current methods suffer from information disconnection and limited receptive field, especially for the sparse distant points. In this work, we study the varying-sparsity distribution of LiDAR points and present SphereFormer to directly aggregate information from dense close points to the sparse distant ones. We design radial window self-attention that partitions the space into multiple non-overlapping narrow and long windows. It overcomes the disconnection issue and enlarges the receptive field smoothly and dramatically, which significantly boosts the performance of sparse distant points. Moreover, to fit the narrow and long windows, we propose exponential splitting to yield fine-grained position encoding and dynamic feature selection to increase model representation ability. Notably, our method ranks 1st on both nuScenes and SemanticKITTI semantic segmentation benchmarks with 81.9% and 74.8% mIoU, respectively. Also, we achieve the 3rd place on nuScenes object detection benchmark with 72.8% NDS and 68.5% mAP. Code is available at https://github.com/dvlab-research/SphereFormer.git.

Shijia Huang, Yilun Chen, Jiaya Jia et al.

The 3D visual grounding task aims to ground a natural language description to the targeted object in a 3D scene, which is usually represented in 3D point clouds. Previous works studied visual grounding under specific views. The vision-language correspondence learned by this way can easily fail once the view changes. In this paper, we propose a Multi-View Transformer (MVT) for 3D visual grounding. We project the 3D scene to a multi-view space, in which the position information of the 3D scene under different views are modeled simultaneously and aggregated together. The multi-view space enables the network to learn a more robust multi-modal representation for 3D visual grounding and eliminates the dependence on specific views. Extensive experiments show that our approach significantly outperforms all state-of-the-art methods. Specifically, on Nr3D and Sr3D datasets, our method outperforms the best competitor by 11.2% and 7.1% and even surpasses recent work with extra 2D assistance by 5.9% and 6.6%. Our code is available at https://github.com/sega-hsj/MVT-3DVG.

Yanwei Li, Xiaojuan Qi, Yukang Chen et al.

In this work, we present a conceptually simple yet effective framework for cross-modality 3D object detection, named voxel field fusion. The proposed approach aims to maintain cross-modality consistency by representing and fusing augmented image features as a ray in the voxel field. To this end, the learnable sampler is first designed to sample vital features from the image plane that are projected to the voxel grid in a point-to-ray manner, which maintains the consistency in feature representation with spatial context. In addition, ray-wise fusion is conducted to fuse features with the supplemental context in the constructed voxel field. We further develop mixed augmentor to align feature-variant transformations, which bridges the modality gap in data augmentation. The proposed framework is demonstrated to achieve consistent gains in various benchmarks and outperforms previous fusion-based methods on KITTI and nuScenes datasets. Code is made available at https://github.com/dvlab-research/VFF.

Yilun Chen, Zhiding Yu, Yukang Chen et al.

False negatives (FN) in 3D object detection, {\em e.g.}, missing predictions of pedestrians, vehicles, or other obstacles, can lead to potentially dangerous situations in autonomous driving. While being fatal, this issue is understudied in many current 3D detection methods. In this work, we propose Hard Instance Probing (HIP), a general pipeline that identifies \textit{FN} in a multi-stage manner and guides the models to focus on excavating difficult instances. For 3D object detection, we instantiate this method as FocalFormer3D, a simple yet effective detector that excels at excavating difficult objects and improving prediction recall. FocalFormer3D features a multi-stage query generation to discover hard objects and a box-level transformer decoder to efficiently distinguish objects from massive object candidates. Experimental results on the nuScenes and Waymo datasets validate the superior performance of FocalFormer3D. The advantage leads to strong performance on both detection and tracking, in both LiDAR and multi-modal settings. Notably, FocalFormer3D achieves a 70.5 mAP and 73.9 NDS on nuScenes detection benchmark, while the nuScenes tracking benchmark shows 72.1 AMOTA, both ranking 1st place on the nuScenes LiDAR leaderboard. Our code is available at \url{https://github.com/NVlabs/FocalFormer3D}.

Jiequan Cui, Zhisheng Zhong, Zhuotao Tian et al.

In this paper, we propose the Generalized Parametric Contrastive Learning (GPaCo/PaCo) which works well on both imbalanced and balanced data. Based on theoretical analysis, we observe that supervised contrastive loss tends to bias high-frequency classes and thus increases the difficulty of imbalanced learning. We introduce a set of parametric class-wise learnable centers to rebalance from an optimization perspective. Further, we analyze our GPaCo/PaCo loss under a balanced setting. Our analysis demonstrates that GPaCo/PaCo can adaptively enhance the intensity of pushing samples of the same class close as more samples are pulled together with their corresponding centers and benefit hard example learning. Experiments on long-tailed benchmarks manifest the new state-of-the-art for long-tailed recognition. On full ImageNet, models from CNNs to vision transformers trained with GPaCo loss show better generalization performance and stronger robustness compared with MAE models. Moreover, GPaCo can be applied to the semantic segmentation task and obvious improvements are observed on the 4 most popular benchmarks. Our code is available at https://github.com/dvlab-research/Parametric-Contrastive-Learning.

Zhisheng Zhong, Jiequan Cui, Yibo Yang et al.

A recent study has shown a phenomenon called neural collapse in that the within-class means of features and the classifier weight vectors converge to the vertices of a simplex equiangular tight frame at the terminal phase of training for classification. In this paper, we explore the corresponding structures of the last-layer feature centers and classifiers in semantic segmentation. Based on our empirical and theoretical analysis, we point out that semantic segmentation naturally brings contextual correlation and imbalanced distribution among classes, which breaks the equiangular and maximally separated structure of neural collapse for both feature centers and classifiers. However, such a symmetric structure is beneficial to discrimination for the minor classes. To preserve these advantages, we introduce a regularizer on feature centers to encourage the network to learn features closer to the appealing structure in imbalanced semantic segmentation. Experimental results show that our method can bring significant improvements on both 2D and 3D semantic segmentation benchmarks. Moreover, our method ranks 1st and sets a new record (+6.8% mIoU) on the ScanNet200 test leaderboard. Code will be available at https://github.com/dvlab-research/Imbalanced-Learning.

Xin Lai, Zhuotao Tian, Xiaogang Xu et al.

Unsupervised domain adaptation in semantic segmentation has been raised to alleviate the reliance on expensive pixel-wise annotations. It leverages a labeled source domain dataset as well as unlabeled target domain images to learn a segmentation network. In this paper, we observe two main issues of the existing domain-invariant learning framework. (1) Being distracted by the feature distribution alignment, the network cannot focus on the segmentation task. (2) Fitting source domain data well would compromise the target domain performance. To address these issues, we propose DecoupleNet that alleviates source domain overfitting and enables the final model to focus more on the segmentation task. Furthermore, we put forward Self-Discrimination (SD) and introduce an auxiliary classifier to learn more discriminative target domain features with pseudo labels. Finally, we propose Online Enhanced Self-Training (OEST) to contextually enhance the quality of pseudo labels in an online manner. Experiments show our method outperforms existing state-of-the-art methods, and extensive ablation studies verify the effectiveness of each component. Code is available at https://github.com/dvlab-research/DecoupleNet.

Zetong Yang, Li Jiang, Yanan Sun et al.

3D point cloud understanding is an important component in autonomous driving and robotics. In this paper, we present a novel Embedding-Querying paradigm (EQ- Paradigm) for 3D understanding tasks including detection, segmentation, and classification. EQ-Paradigm is a unified paradigm that enables the combination of any existing 3D backbone architectures with different task heads. Under the EQ-Paradigm, the input is firstly encoded in the embedding stage with an arbitrary feature extraction architecture, which is independent of tasks and heads. Then, the querying stage enables the encoded features to be applicable for diverse task heads. This is achieved by introducing an intermediate representation, i.e., Q-representation, in the querying stage to serve as a bridge between the embedding stage and task heads. We design a novel Q- Net as the querying stage network. Extensive experimental results on various 3D tasks, including object detection, semantic segmentation and shape classification, show that EQ-Paradigm in tandem with Q-Net is a general and effective pipeline, which enables a flexible collaboration of backbones and heads, and further boosts the performance of the state-of-the-art methods. Codes and models are available at https://github.com/dvlab-research/DeepVision3D.

Yilun Chen, Shijia Huang, Shu Liu et al.

Camera-based 3D object detectors are welcome due to their wider deployment and lower price than LiDAR sensors. We first revisit the prior stereo detector DSGN for its stereo volume construction ways for representing both 3D geometry and semantics. We polish the stereo modeling and propose the advanced version, DSGN++, aiming to enhance effective information flow throughout the 2D-to-3D pipeline in three main aspects. First, to effectively lift the 2D information to stereo volume, we propose depth-wise plane sweeping (DPS) that allows denser connections and extracts depth-guided features. Second, for grasping differently spaced features, we present a novel stereo volume -- Dual-view Stereo Volume (DSV) that integrates front-view and top-view features and reconstructs sub-voxel depth in the camera frustum. Third, as the foreground region becomes less dominant in 3D space, we propose a multi-modal data editing strategy -- Stereo-LiDAR Copy-Paste, which ensures cross-modal alignment and improves data efficiency. Without bells and whistles, extensive experiments in various modality setups on the popular KITTI benchmark show that our method consistently outperforms other camera-based 3D detectors for all categories. Code is available at https://github.com/chenyilun95/DSGN2.

Zhuotao Tian, Jiequan Cui, Li Jiang et al.

Semantic segmentation is still a challenging task for parsing diverse contexts in different scenes, thus the fixed classifier might not be able to well address varying feature distributions during testing. Different from the mainstream literature where the efficacy of strong backbones and effective decoder heads has been well studied, in this paper, additional contextual hints are instead exploited via learning a context-aware classifier whose content is data-conditioned, decently adapting to different latent distributions. Since only the classifier is dynamically altered, our method is model-agnostic and can be easily applied to generic segmentation models. Notably, with only negligible additional parameters and +2\% inference time, decent performance gain has been achieved on both small and large models with challenging benchmarks, manifesting substantial practical merits brought by our simple yet effective method. The implementation is available at \url{https://github.com/tianzhuotao/CAC}.

Wenbo Li, Xin Yu, Kun Zhou et al.

Generative adversarial networks (GANs) have made great success in image inpainting yet still have difficulties tackling large missing regions. In contrast, iterative probabilistic algorithms, such as autoregressive and denoising diffusion models, have to be deployed with massive computing resources for decent effect. To achieve high-quality results with low computational cost, we present a novel pixel spread model (PSM) that iteratively employs decoupled probabilistic modeling, combining the optimization efficiency of GANs with the prediction tractability of probabilistic models. As a result, our model selectively spreads informative pixels throughout the image in a few iterations, largely enhancing the completion quality and efficiency. On multiple benchmarks, we achieve new state-of-the-art performance. Code is released at https://github.com/fenglinglwb/PSM.

Jingyao Li, Pengguang Chen, Shengju Qian et al.

Contrastive Language-Image Pre-training (CLIP) has recently shown great promise in pixel-level zero-shot learning tasks. However, existing approaches utilizing CLIP's text and patch embeddings to generate semantic masks often misidentify input pixels from unseen classes, leading to confusion between novel classes and semantically similar ones. In this work, we propose a novel approach, TagCLIP (Trusty-aware guided CLIP), to address this issue. We disentangle the ill-posed optimization problem into two parallel processes: semantic matching performed individually and reliability judgment for improving discrimination ability. Building on the idea of special tokens in language modeling representing sentence-level embeddings, we introduce a trusty token that enables distinguishing novel classes from known ones in prediction. To evaluate our approach, we conduct experiments on two benchmark datasets, PASCAL VOC 2012, COCO-Stuff 164K and PASCAL Context. Our results show that TagCLIP improves the Intersection over Union (IoU) of unseen classes by 7.4%, 1.7% and 2.1%, respectively, with negligible overheads. The code is available at https://github.com/dvlab-research/TagCLIP.

Yukang Chen, Shengju Qian, Haotian Tang et al. · mit

We present LongLoRA, an efficient fine-tuning approach that extends the context sizes of pre-trained large language models (LLMs), with limited computation cost. Typically, training LLMs with long context sizes is computationally expensive, requiring extensive training hours and GPU resources. For example, training on the context length of 8192 needs 16x computational costs in self-attention layers as that of 2048. In this paper, we speed up the context extension of LLMs in two aspects. On the one hand, although dense global attention is needed during inference, fine-tuning the model can be effectively and efficiently done by sparse local attention. The proposed shifted sparse attention effectively enables context extension, leading to non-trivial computation saving with similar performance to fine-tuning with vanilla attention. Particularly, it can be implemented with only two lines of code in training, while being optional in inference. On the other hand, we revisit the parameter-efficient fine-tuning regime for context expansion. Notably, we find that LoRA for context extension works well under the premise of trainable embedding and normalization. LongLoRA combines this improved LoRA with S^2-Attn. LongLoRA demonstrates strong empirical results on various tasks on Llama2 models from 7B/13B to 70B. LongLoRA extends Llama2 7B from 4k context to 100k, or Llama2 70B to 32k on a single 8x A100 machine. LongLoRA extends models' context while retaining their original architectures, and is compatible with most existing techniques, like Flash-Attention2. In addition, we further conduct supervised fine-tuning with LongLoRA and our long instruction-following LongAlpaca dataset.

Zhisheng Zhong, Jiequan Cui, Zeming Li et al.

Deep neural networks perform poorly on heavily class-imbalanced datasets. Given the promising performance of contrastive learning, we propose Rebalanced Siamese Contrastive Mining (ResCom) to tackle imbalanced recognition. Based on the mathematical analysis and simulation results, we claim that supervised contrastive learning suffers a dual class-imbalance problem at both the original batch and Siamese batch levels, which is more serious than long-tailed classification learning. In this paper, at the original batch level, we introduce a class-balanced supervised contrastive loss to assign adaptive weights for different classes. At the Siamese batch level, we present a class-balanced queue, which maintains the same number of keys for all classes. Furthermore, we note that the imbalanced contrastive loss gradient with respect to the contrastive logits can be decoupled into the positives and negatives, and easy positives and easy negatives will make the contrastive gradient vanish. We propose supervised hard positive and negative pairs mining to pick up informative pairs for contrastive computation and improve representation learning. Finally, to approximately maximize the mutual information between the two views, we propose Siamese Balanced Softmax and joint it with the contrastive loss for one-stage training. Extensive experiments demonstrate that ResCom outperforms the previous methods by large margins on multiple long-tailed recognition benchmarks. Our code and models are made publicly available at: https://github.com/dvlab-research/ResCom.

Xin Lai, Yuhui Yuan, Ruihang Chu et al.

Recently, transformer-based methods have dominated 3D instance segmentation, where mask attention is commonly involved. Specifically, object queries are guided by the initial instance masks in the first cross-attention, and then iteratively refine themselves in a similar manner. However, we observe that the mask-attention pipeline usually leads to slow convergence due to low-recall initial instance masks. Therefore, we abandon the mask attention design and resort to an auxiliary center regression task instead. Through center regression, we effectively overcome the low-recall issue and perform cross-attention by imposing positional prior. To reach this goal, we develop a series of position-aware designs. First, we learn a spatial distribution of 3D locations as the initial position queries. They spread over the 3D space densely, and thus can easily capture the objects in a scene with a high recall. Moreover, we present relative position encoding for the cross-attention and iterative refinement for more accurate position queries. Experiments show that our approach converges 4x faster than existing work, sets a new state of the art on ScanNetv2 3D instance segmentation benchmark, and also demonstrates superior performance across various datasets. Code and models are available at https://github.com/dvlab-research/Mask-Attention-Free-Transformer.

Longxiang Tang, Zhuotao Tian, Kai Li et al.

This study addresses the Domain-Class Incremental Learning problem, a realistic but challenging continual learning scenario where both the domain distribution and target classes vary across tasks. To handle these diverse tasks, pre-trained Vision-Language Models (VLMs) are introduced for their strong generalizability. However, this incurs a new problem: the knowledge encoded in the pre-trained VLMs may be disturbed when adapting to new tasks, compromising their inherent zero-shot ability. Existing methods tackle it by tuning VLMs with knowledge distillation on extra datasets, which demands heavy computation overhead. To address this problem efficiently, we propose the Distribution-aware Interference-free Knowledge Integration (DIKI) framework, retaining pre-trained knowledge of VLMs from a perspective of avoiding information interference. Specifically, we design a fully residual mechanism to infuse newly learned knowledge into a frozen backbone, while introducing minimal adverse impacts on pre-trained knowledge. Besides, this residual property enables our distribution-aware integration calibration scheme, explicitly controlling the information implantation process for test data from unseen distributions. Experiments demonstrate that our DIKI surpasses the current state-of-the-art approach using only 0.86% of the trained parameters and requiring substantially less training time. Code is available at: https://github.com/lloongx/DIKI .

Yukang Chen, Jianhui Liu, Xiangyu Zhang et al.

3D object detectors usually rely on hand-crafted proxies, e.g., anchors or centers, and translate well-studied 2D frameworks to 3D. Thus, sparse voxel features need to be densified and processed by dense prediction heads, which inevitably costs extra computation. In this paper, we instead propose VoxelNext for fully sparse 3D object detection. Our core insight is to predict objects directly based on sparse voxel features, without relying on hand-crafted proxies. Our strong sparse convolutional network VoxelNeXt detects and tracks 3D objects through voxel features entirely. It is an elegant and efficient framework, with no need for sparse-to-dense conversion or NMS post-processing. Our method achieves a better speed-accuracy trade-off than other mainframe detectors on the nuScenes dataset. For the first time, we show that a fully sparse voxel-based representation works decently for LIDAR 3D object detection and tracking. Extensive experiments on nuScenes, Waymo, and Argoverse2 benchmarks validate the effectiveness of our approach. Without bells and whistles, our model outperforms all existing LIDAR methods on the nuScenes tracking test benchmark.

Shaoteng Liu, Yuechen Zhang, Wenbo Li et al.

This paper presents Video-P2P, a novel framework for real-world video editing with cross-attention control. While attention control has proven effective for image editing with pre-trained image generation models, there are currently no large-scale video generation models publicly available. Video-P2P addresses this limitation by adapting an image generation diffusion model to complete various video editing tasks. Specifically, we propose to first tune a Text-to-Set (T2S) model to complete an approximate inversion and then optimize a shared unconditional embedding to achieve accurate video inversion with a small memory cost. For attention control, we introduce a novel decoupled-guidance strategy, which uses different guidance strategies for the source and target prompts. The optimized unconditional embedding for the source prompt improves reconstruction ability, while an initialized unconditional embedding for the target prompt enhances editability. Incorporating the attention maps of these two branches enables detailed editing. These technical designs enable various text-driven editing applications, including word swap, prompt refinement, and attention re-weighting. Video-P2P works well on real-world videos for generating new characters while optimally preserving their original poses and scenes. It significantly outperforms previous approaches.

Bohao Peng, Zhuotao Tian, Xiaoyang Wu et al.

Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve 50.0% mIoU on COCO dataset one-shot setting and 56.0% on five-shot segmentation, respectively. The code will be available on the project website. We hope our work can benefit broader industrial applications where novel classes with limited annotations are required to be decently identified.

Bohao Peng, Zhuotao Tian, Xiaoyang Wu et al.

Few-shot semantic segmentation (FSS) aims to form class-agnostic models segmenting unseen classes with only a handful of annotations. Previous methods limited to the semantic feature and prototype representation suffer from coarse segmentation granularity and train-set overfitting. In this work, we design Hierarchically Decoupled Matching Network (HDMNet) mining pixel-level support correlation based on the transformer architecture. The self-attention modules are used to assist in establishing hierarchical dense features, as a means to accomplish the cascade matching between query and support features. Moreover, we propose a matching module to reduce train-set overfitting and introduce correlation distillation leveraging semantic correspondence from coarse resolution to boost fine-grained segmentation. Our method performs decently in experiments. We achieve $50.0\%$ mIoU on \coco~dataset one-shot setting and $56.0\%$ on five-shot segmentation, respectively.

Tao Hu, Shu Liu, Yilun Chen et al.

Neural Radiance Fields (NeRF) has been wildly applied to various tasks for its high-quality representation of 3D scenes. It takes long per-scene training time and per-image testing time. In this paper, we present EfficientNeRF as an efficient NeRF-based method to represent 3D scene and synthesize novel-view images. Although several ways exist to accelerate the training or testing process, it is still difficult to much reduce time for both phases simultaneously. We analyze the density and weight distribution of the sampled points then propose valid and pivotal sampling at the coarse and fine stage, respectively, to significantly improve sampling efficiency. In addition, we design a novel data structure to cache the whole scene during testing to accelerate the rendering speed. Overall, our method can reduce over 88\% of training time, reach rendering speed of over 200 FPS, while still achieving competitive accuracy. Experiments prove that our method promotes the practicality of NeRF in the real world and enables many applications.

Yukang Chen, Jianhui Liu, Xiangyu Zhang et al.

Recent advance in 2D CNNs has revealed that large kernels are important. However, when directly applying large convolutional kernels in 3D CNNs, severe difficulties are met, where those successful module designs in 2D become surprisingly ineffective on 3D networks, including the popular depth-wise convolution. To address this vital challenge, we instead propose the spatial-wise partition convolution and its large-kernel module. As a result, it avoids the optimization and efficiency issues of naive 3D large kernels. Our large-kernel 3D CNN network, LargeKernel3D, yields notable improvement in 3D tasks of semantic segmentation and object detection. It achieves 73.9% mIoU on the ScanNetv2 semantic segmentation and 72.8% NDS nuScenes object detection benchmarks, ranking 1st on the nuScenes LIDAR leaderboard. The performance further boosts to 74.2% NDS with a simple multi-modal fusion. In addition, LargeKernel3D can be scaled to 17x17x17 kernel size on Waymo 3D object detection. For the first time, we show that large kernels are feasible and essential for 3D visual tasks.

Yanwei Li, Chengyao Wang, Jiaya Jia

In this work, we present a novel method to tackle the token generation challenge in Vision Language Models (VLMs) for video and image understanding, called LLaMA-VID. Current VLMs, while proficient in tasks like image captioning and visual question answering, face computational burdens when processing long videos due to the excessive visual tokens. LLaMA-VID addresses this issue by representing each frame with two distinct tokens, namely context token and content token. The context token encodes the overall image context based on user input, whereas the content token encapsulates visual cues in each frame. This dual-token strategy significantly reduces the overload of long videos while preserving critical information. Generally, LLaMA-VID empowers existing frameworks to support hour-long videos and pushes their upper limit with an extra context token. It is proved to surpass previous methods on most of video- or image-based benchmarks. Code is available https://github.com/dvlab-research/LLaMA-VID}{https://github.com/dvlab-research/LLaMA-VID

Jinhui Ye, Ning Gao, Senqiao Yang et al. · tsinghua

Vision-Language-Action (VLA) models have recently emerged as a promising paradigm for building general-purpose robotic agents. However, the VLA landscape remains highly fragmented and complex: as existing approaches vary substantially in architectures, training data, embodiment configurations, and benchmark-specific engineering. In this work, we introduce StarVLA-$α$, a simple yet strong baseline designed to study VLA design choices under controlled conditions. StarVLA-$α$ deliberately minimizes architectural and pipeline complexity to reduce experimental confounders and enable systematic analysis. Specifically, we re-evaluate several key design axes, including action modeling strategies, robot-specific pretraining, and interface engineering. Across unified multi-benchmark training on LIBERO, SimplerEnv, RoboTwin, and RoboCasa, the same simple baseline remains highly competitive, indicating that a strong VLM backbone combined with minimal design is already sufficient to achieve strong performance without relying on additional architectural complexity or engineering tricks. Notably, our single generalist model outperforms $π_{0.5}$ by 20\% on the public real-world RoboChallenge benchmark. We expect StarVLA-$α$ to serve as a solid starting point for future research in the VLA regime. Code will be released at https://github.com/starVLA/starVLA.

Lu Qi, Jason Kuen, Weidong Guo et al.

Dense image segmentation tasks e.g., semantic, panoptic) are useful for image editing, but existing methods can hardly generalize well in an in-the-wild setting where there are unrestricted image domains, classes, and image resolution and quality variations. Motivated by these observations, we construct a new entity segmentation dataset, with a strong focus on high-quality dense segmentation in the wild. The dataset contains images spanning diverse image domains and entities, along with plentiful high-resolution images and high-quality mask annotations for training and testing. Given the high-quality and -resolution nature of the dataset, we propose CropFormer which is designed to tackle the intractability of instance-level segmentation on high-resolution images. It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image. CropFormer is the first query-based Transformer architecture that can effectively fuse mask predictions from multiple image views, by learning queries that effectively associate the same entities across the full image and its crop. With CropFormer, we achieve a significant AP gain of $1.9$ on the challenging entity segmentation task. Furthermore, CropFormer consistently improves the accuracy of traditional segmentation tasks and datasets. The dataset and code will be released at http://luqi.info/entityv2.github.io/.

Jingyao Li, Pengguang Chen, Shaozuo Yu et al.

The core of out-of-distribution (OOD) detection is to learn the in-distribution (ID) representation, which is distinguishable from OOD samples. Previous work applied recognition-based methods to learn the ID features, which tend to learn shortcuts instead of comprehensive representations. In this work, we find surprisingly that simply using reconstruction-based methods could boost the performance of OOD detection significantly. We deeply explore the main contributors of OOD detection and find that reconstruction-based pretext tasks have the potential to provide a generally applicable and efficacious prior, which benefits the model in learning intrinsic data distributions of the ID dataset. Specifically, we take Masked Image Modeling as a pretext task for our OOD detection framework (MOOD). Without bells and whistles, MOOD outperforms previous SOTA of one-class OOD detection by 5.7%, multi-class OOD detection by 3.0%, and near-distribution OOD detection by 2.1%. It even defeats the 10-shot-per-class outlier exposure OOD detection, although we do not include any OOD samples for our detection

Zelin Zhao, Ze Wu, Yueqing Zhuang et al.

Multi-object tracking (MOT) requires detecting and associating objects through frames. Unlike tracking via detected bounding boxes or tracking objects as points, we propose tracking objects as pixel-wise distributions. We instantiate this idea on a transformer-based architecture, P3AFormer, with pixel-wise propagation, prediction, and association. P3AFormer propagates pixel-wise features guided by flow information to pass messages between frames. Furthermore, P3AFormer adopts a meta-architecture to produce multi-scale object feature maps. During inference, a pixel-wise association procedure is proposed to recover object connections through frames based on the pixel-wise prediction. P3AFormer yields 81.2\% in terms of MOTA on the MOT17 benchmark -- the first among all transformer networks to reach 80\% MOTA in literature. P3AFormer also outperforms state-of-the-arts on the MOT20 and KITTI benchmarks.

Ruihang Chu, Enze Xie, Shentong Mo et al.

We introduce a new diffusion-based approach for shape completion on 3D range scans. Compared with prior deterministic and probabilistic methods, we strike a balance between realism, multi-modality, and high fidelity. We propose DiffComplete by casting shape completion as a generative task conditioned on the incomplete shape. Our key designs are two-fold. First, we devise a hierarchical feature aggregation mechanism to inject conditional features in a spatially-consistent manner. So, we can capture both local details and broader contexts of the conditional inputs to control the shape completion. Second, we propose an occupancy-aware fusion strategy in our model to enable the completion of multiple partial shapes and introduce higher flexibility on the input conditions. DiffComplete sets a new SOTA performance (e.g., 40% decrease on l_1 error) on two large-scale 3D shape completion benchmarks. Our completed shapes not only have a realistic outlook compared with the deterministic methods but also exhibit high similarity to the ground truths compared with the probabilistic alternatives. Further, DiffComplete has strong generalizability on objects of entirely unseen classes for both synthetic and real data, eliminating the need for model re-training in various applications.

Yuechen Zhang, Zexin He, Jinbo Xing et al.

Current 3D scene stylization methods transfer textures and colors as styles using arbitrary style references, lacking meaningful semantic correspondences. We introduce Reference-Based Non-Photorealistic Radiance Fields (Ref-NPR) to address this limitation. This controllable method stylizes a 3D scene using radiance fields with a single stylized 2D view as a reference. We propose a ray registration process based on the stylized reference view to obtain pseudo-ray supervision in novel views. Then we exploit semantic correspondences in content images to fill occluded regions with perceptually similar styles, resulting in non-photorealistic and continuous novel view sequences. Our experimental results demonstrate that Ref-NPR outperforms existing scene and video stylization methods regarding visual quality and semantic correspondence. The code and data are publicly available on the project page at https://ref-npr.github.io.

Tao Hu, Xiaogang Xu, Shu Liu et al.

Synthesizing photo-realistic images from a point cloud is challenging because of the sparsity of point cloud representation. Recent Neural Radiance Fields and extensions are proposed to synthesize realistic images from 2D input. In this paper, we present Point2Pix as a novel point renderer to link the 3D sparse point clouds with 2D dense image pixels. Taking advantage of the point cloud 3D prior and NeRF rendering pipeline, our method can synthesize high-quality images from colored point clouds, generally for novel indoor scenes. To improve the efficiency of ray sampling, we propose point-guided sampling, which focuses on valid samples. Also, we present Point Encoding to build Multi-scale Radiance Fields that provide discriminative 3D point features. Finally, we propose Fusion Encoding to efficiently synthesize high-quality images. Extensive experiments on the ScanNet and ArkitScenes datasets demonstrate the effectiveness and generalization.

Tao Hu, Xiaogang Xu, Ruihang Chu et al.

Existing learning-based methods for point cloud rendering adopt various 3D representations and feature querying mechanisms to alleviate the sparsity problem of point clouds. However, artifacts still appear in rendered images, due to the challenges in extracting continuous and discriminative 3D features from point clouds. In this paper, we present a dense while lightweight 3D representation, named TriVol, that can be combined with NeRF to render photo-realistic images from point clouds. Our TriVol consists of triple slim volumes, each of which is encoded from the point cloud. TriVol has two advantages. First, it fuses respective fields at different scales and thus extracts local and non-local features for discriminative representation. Second, since the volume size is greatly reduced, our 3D decoder can be efficiently inferred, allowing us to increase the resolution of the 3D space to render more point details. Extensive experiments on different benchmarks with varying kinds of scenes/objects demonstrate our framework's effectiveness compared with current approaches. Moreover, our framework has excellent generalization ability to render a category of scenes/objects without fine-tuning.

Jiequan Cui, Yuhui Yuan, Zhisheng Zhong et al.

In this paper, we study the problem of class imbalance in semantic segmentation. We first investigate and identify the main challenges of addressing this issue through pixel rebalance. Then a simple and yet effective region rebalance scheme is derived based on our analysis. In our solution, pixel features belonging to the same class are grouped into region features, and a rebalanced region classifier is applied via an auxiliary region rebalance branch during training. To verify the flexibility and effectiveness of our method, we apply the region rebalance module into various semantic segmentation methods, such as Deeplabv3+, OCRNet, and Swin. Our strategy achieves consistent improvement on the challenging ADE20K and COCO-Stuff benchmark. In particular, with the proposed region rebalance scheme, state-of-the-art BEiT receives +0.7% gain in terms of mIoU on the ADE20K val set.

Shengju Qian, Yi Zhu, Wenbo Li et al.

The architecture of transformers, which recently witness booming applications in vision tasks, has pivoted against the widespread convolutional paradigm. Relying on the tokenization process that splits inputs into multiple tokens, transformers are capable of extracting their pairwise relationships using self-attention. While being the stemming building block of transformers, what makes for a good tokenizer has not been well understood in computer vision. In this work, we investigate this uncharted problem from an information trade-off perspective. In addition to unifying and understanding existing structural modifications, our derivation leads to better design strategies for vision tokenizers. The proposed Modulation across Tokens (MoTo) incorporates inter-token modeling capability through normalization. Furthermore, a regularization objective TokenProp is embraced in the standard training regime. Through extensive experiments on various transformer architectures, we observe both improved performance and intriguing properties of these two plug-and-play designs with negligible computational overhead. These observations further indicate the importance of the commonly-omitted designs of tokenizers in vision transformer.

Xiaogang Xu, Ruixing Wang, Chi-Wing Fu et al.

Despite the quality improvement brought by the recent methods, video super-resolution (SR) is still very challenging, especially for videos that are low-light and noisy. The current best solution is to subsequently employ best models of video SR, denoising, and illumination enhancement, but doing so often lowers the image quality, due to the inconsistency between the models. This paper presents a new parametric representation called the Deep Parametric 3D Filters (DP3DF), which incorporates local spatiotemporal information to enable simultaneous denoising, illumination enhancement, and SR efficiently in a single encoder-and-decoder network. Also, a dynamic residual frame is jointly learned with the DP3DF via a shared backbone to further boost the SR quality. We performed extensive experiments, including a large-scale user study, to show our method's effectiveness. Our method consistently surpasses the best state-of-the-art methods on all the challenging real datasets with top PSNR and user ratings, yet having a very fast run time.

Shengju Qian, Huiwen Chang, Yuanzhen Li et al.

We propose Stratified Image Transformer(StraIT), a pure non-autoregressive(NAR) generative model that demonstrates superiority in high-quality image synthesis over existing autoregressive(AR) and diffusion models(DMs). In contrast to the under-exploitation of visual characteristics in existing vision tokenizer, we leverage the hierarchical nature of images to encode visual tokens into stratified levels with emergent properties. Through the proposed image stratification that obtains an interlinked token pair, we alleviate the modeling difficulty and lift the generative power of NAR models. Our experiments demonstrate that StraIT significantly improves NAR generation and out-performs existing DMs and AR methods while being order-of-magnitude faster, achieving FID scores of 3.96 at 256*256 resolution on ImageNet without leveraging any guidance in sampling or auxiliary image classifiers. When equipped with classifier-free guidance, our method achieves an FID of 3.36 and IS of 259.3. In addition, we illustrate the decoupled modeling process of StraIT generation, showing its compelling properties on applications including domain transfer.

Zelin Zhao, Jiaya Jia

In this paper, we present a simple seq2seq formulation for view synthesis where we take a set of ray points as input and output colors corresponding to the rays. Directly applying a standard transformer on this seq2seq formulation has two limitations. First, the standard attention cannot successfully fit the volumetric rendering procedure, and therefore high-frequency components are missing in the synthesized views. Second, applying global attention to all rays and pixels is extremely inefficient. Inspired by the neural radiance field (NeRF), we propose the NeRF attention (NeRFA) to address the above problems. On the one hand, NeRFA considers the volumetric rendering equation as a soft feature modulation procedure. In this way, the feature modulation enhances the transformers with the NeRF-like inductive bias. On the other hand, NeRFA performs multi-stage attention to reduce the computational overhead. Furthermore, the NeRFA model adopts the ray and pixel transformers to learn the interactions between rays and pixels. NeRFA demonstrates superior performance over NeRF and NerFormer on four datasets: DeepVoxels, Blender, LLFF, and CO3D. Besides, NeRFA establishes a new state-of-the-art under two settings: the single-scene view synthesis and the category-centric novel view synthesis.

Xiaogang Xu, Hengshuang Zhao, Philip Torr et al.

Deep Neural Networks (DNNs) are vulnerable to the black-box adversarial attack that is highly transferable. This threat comes from the distribution gap between adversarial and clean samples in feature space of the target DNNs. In this paper, we use Deep Generative Networks (DGNs) with a novel training mechanism to eliminate the distribution gap. The trained DGNs align the distribution of adversarial samples with clean ones for the target DNNs by translating pixel values. Different from previous work, we propose a more effective pixel level training constraint to make this achievable, thus enhancing robustness on adversarial samples. Further, a class-aware feature-level constraint is formulated for integrated distribution alignment. Our approach is general and applicable to multiple tasks, including image classification, semantic segmentation, and object detection. We conduct extensive experiments on different datasets. Our strategy demonstrates its unique effectiveness and generality against black-box attacks.

Liying Lu, Ruizheng Wu, Huaijia Lin et al.

Video frame interpolation (VFI), which aims to synthesize intermediate frames of a video, has made remarkable progress with development of deep convolutional networks over past years. Existing methods built upon convolutional networks generally face challenges of handling large motion due to the locality of convolution operations. To overcome this limitation, we introduce a novel framework, which takes advantage of Transformer to model long-range pixel correlation among video frames. Further, our network is equipped with a novel cross-scale window-based attention mechanism, where cross-scale windows interact with each other. This design effectively enlarges the receptive field and aggregates multi-scale information. Extensive quantitative and qualitative experiments demonstrate that our method achieves new state-of-the-art results on various benchmarks.

Yixin Chen, Shuai Zhang, Boran Han et al. · amazon-science

In-context learning (ICL) involves reasoning from given contextual examples. As more modalities comes, this procedure is becoming more challenging as the interleaved input modalities convolutes the understanding process. This is exemplified by the observation that multimodal models often struggle to effectively extrapolate from contextual examples to perform ICL. To address these challenges, we introduce MultiModal In-conteXt Tuning (M$^2$IXT), a lightweight module to enhance the ICL capabilities of multimodal unified models. The proposed M$^2$IXT module perceives an expandable context window to incorporate various labeled examples of multiple modalities (e.g., text, image, and coordinates). It can be prepended to various multimodal unified models (e.g., OFA, Unival, LLaVA) of different architectures and trained via a mixed-tasks strategy to enable rapid few-shot adaption on multiple tasks and datasets. When tuned on as little as 50K multimodal data, M$^2$IXT can boost the few-shot ICL performance significantly (e.g., 18\% relative increase for OFA), and obtained state-of-the-art results across an array of tasks including visual question answering, image captioning, visual grounding, and visual entailment, while being considerably small in terms of model parameters (e.g., $\sim$$20\times$ smaller than Flamingo or MMICL), highlighting the flexibility and effectiveness of M$^2$IXT as a multimodal in-context learner.

Shaoteng Liu, Xiangyu Zhang, Tao Hu et al.

We present view-synthesis autoencoders (VSA) in this paper, which is a self-supervised learning framework designed for vision transformers. Different from traditional 2D pretraining methods, VSA can be pre-trained with multi-view data. In each iteration, the input to VSA is one view (or multiple views) of a 3D object and the output is a synthesized image in another target pose. The decoder of VSA has several cross-attention blocks, which use the source view as value, source pose as key, and target pose as query. They achieve cross-attention to synthesize the target view. This simple approach realizes large-angle view synthesis and learns spatial invariant representation, where the latter is decent initialization for transformers on downstream tasks, such as 3D classification on ModelNet40, ShapeNet Core55, and ScanObjectNN. VSA outperforms existing methods significantly for linear probing and is competitive for fine-tuning. The code will be made publicly available.

Xiaogang Xu, Yitong Yu, Nianjuan Jiang et al.

To facilitate video denoising research, we construct a compelling dataset, namely, "Practical Video Denoising Dataset" (PVDD), containing 200 noisy-clean dynamic video pairs in both sRGB and RAW format. Compared with existing datasets consisting of limited motion information, PVDD covers dynamic scenes with varying and natural motion. Different from datasets using primarily Gaussian or Poisson distributions to synthesize noise in the sRGB domain, PVDD synthesizes realistic noise from the RAW domain with a physically meaningful sensor noise model followed by ISP processing. Moreover, we also propose a new video denoising framework, called Recurrent Video Denoising Transformer (RVDT), which can achieve SOTA performance on PVDD and other current video denoising benchmarks. RVDT consists of both spatial and temporal transformer blocks to conduct denoising with long-range operations on the spatial dimension and long-term propagation on the temporal dimension. Especially, RVDT exploits the attention mechanism to implement the bi-directional feature propagation with both implicit and explicit temporal modeling. Extensive experiments demonstrate that 1) models trained on PVDD achieve superior denoising performance on many challenging real-world videos than on models trained on other existing datasets; 2) trained on the same dataset, our proposed RVDT can have better denoising performance than other types of networks.

Yixin Chen, Zhuotao Tian, Pengguang Chen et al.

We revisit the one- and two-stage detector distillation tasks and present a simple and efficient semantic-aware framework to fill the gap between them. We address the pixel-level imbalance problem by designing the category anchor to produce a representative pattern for each category and regularize the topological distance between pixels and category anchors to further tighten their semantic bonds. We name our method SEA (SEmantic-aware Alignment) distillation given the nature of abstracting dense fine-grained information by semantic reliance to well facilitate distillation efficacy. SEA is well adapted to either detection pipeline and achieves new state-of-the-art results on the challenging COCO object detection task on both one- and two-stage detectors. Its superior performance on instance segmentation further manifests the generalization ability. Both 2x-distilled RetinaNet and FCOS with ResNet50-FPN outperform their corresponding 3x ResNet101-FPN teacher, arriving 40.64 and 43.06 AP, respectively. Code will be made publicly available.

Bohao Peng, Jian Wang, Yuechen Zhang et al.

Diffusion models have demonstrated remarkable and robust abilities in both image and video generation. To achieve greater control over generated results, researchers introduce additional architectures, such as ControlNet, Adapters and ReferenceNet, to integrate conditioning controls. However, current controllable generation methods often require substantial additional computational resources, especially for video generation, and face challenges in training or exhibit weak control. In this paper, we propose ControlNeXt: a powerful and efficient method for controllable image and video generation. We first design a more straightforward and efficient architecture, replacing heavy additional branches with minimal additional cost compared to the base model. Such a concise structure also allows our method to seamlessly integrate with other LoRA weights, enabling style alteration without the need for additional training. As for training, we reduce up to 90% of learnable parameters compared to the alternatives. Furthermore, we propose another method called Cross Normalization (CN) as a replacement for Zero-Convolution' to achieve fast and stable training convergence. We have conducted various experiments with different base models across images and videos, demonstrating the robustness of our method.

Jiehui Huang, Yuechen Zhang, Xu He et al.

Recent video generation models demonstrate impressive synthesis capabilities but remain limited by single-modality conditioning, constraining their holistic world understanding. This stems from insufficient cross-modal interaction and limited modal diversity for comprehensive world knowledge representation. To address these limitations, we introduce UnityVideo, a unified framework for world-aware video generation that jointly learns across multiple modalities (segmentation masks, human skeletons, DensePose, optical flow, and depth maps) and training paradigms. Our approach features two core components: (1) dynamic noising to unify heterogeneous training paradigms, and (2) a modality switcher with an in-context learner that enables unified processing via modular parameters and contextual learning. We contribute a large-scale unified dataset with 1.3M samples. Through joint optimization, UnityVideo accelerates convergence and significantly enhances zero-shot generalization to unseen data. We demonstrate that UnityVideo achieves superior video quality, consistency, and improved alignment with physical world constraints. Code and data can be found at: https://github.com/dvlab-research/UnityVideo

Yanwei Li, Yuechen Zhang, Chengyao Wang et al.

In this work, we introduce Mini-Gemini, a simple and effective framework enhancing multi-modality Vision Language Models (VLMs). Despite the advancements in VLMs facilitating basic visual dialog and reasoning, a performance gap persists compared to advanced models like GPT-4 and Gemini. We try to narrow the gap by mining the potential of VLMs for better performance and any-to-any workflow from three aspects, i.e., high-resolution visual tokens, high-quality data, and VLM-guided generation. To enhance visual tokens, we propose to utilize an additional visual encoder for high-resolution refinement without increasing the visual token count. We further construct a high-quality dataset that promotes precise image comprehension and reasoning-based generation, expanding the operational scope of current VLMs. In general, Mini-Gemini further mines the potential of VLMs and empowers current frameworks with image understanding, reasoning, and generation simultaneously. Mini-Gemini supports a series of dense and MoE Large Language Models (LLMs) from 2B to 34B. It is demonstrated to achieve leading performance in several zero-shot benchmarks and even surpasses the developed private models. Code and models are available at https://github.com/dvlab-research/MiniGemini.