Minghao Chen

Yuqi Lin, Minghao Chen, Wenxiao Wang et al.

Weakly supervised semantic segmentation (WSSS) with image-level labels is a challenging task. Mainstream approaches follow a multi-stage framework and suffer from high training costs. In this paper, we explore the potential of Contrastive Language-Image Pre-training models (CLIP) to localize different categories with only image-level labels and without further training. To efficiently generate high-quality segmentation masks from CLIP, we propose a novel WSSS framework called CLIP-ES. Our framework improves all three stages of WSSS with special designs for CLIP: 1) We introduce the softmax function into GradCAM and exploit the zero-shot ability of CLIP to suppress the confusion caused by non-target classes and backgrounds. Meanwhile, to take full advantage of CLIP, we re-explore text inputs under the WSSS setting and customize two text-driven strategies: sharpness-based prompt selection and synonym fusion. 2) To simplify the stage of CAM refinement, we propose a real-time class-aware attention-based affinity (CAA) module based on the inherent multi-head self-attention (MHSA) in CLIP-ViTs. 3) When training the final segmentation model with the masks generated by CLIP, we introduced a confidence-guided loss (CGL) focus on confident regions. Our CLIP-ES achieves SOTA performance on Pascal VOC 2012 and MS COCO 2014 while only taking 10% time of previous methods for the pseudo mask generation. Code is available at https://github.com/linyq2117/CLIP-ES.

Bolin Ni, Houwen Peng, Minghao Chen et al.

Contrastive language-image pretraining has shown great success in learning visual-textual joint representation from web-scale data, demonstrating remarkable "zero-shot" generalization ability for various image tasks. However, how to effectively expand such new language-image pretraining methods to video domains is still an open problem. In this work, we present a simple yet effective approach that adapts the pretrained language-image models to video recognition directly, instead of pretraining a new model from scratch. More concretely, to capture the long-range dependencies of frames along the temporal dimension, we propose a cross-frame attention mechanism that explicitly exchanges information across frames. Such module is lightweight and can be plugged into pretrained language-image models seamlessly. Moreover, we propose a video-specific prompting scheme, which leverages video content information for generating discriminative textual prompts. Extensive experiments demonstrate that our approach is effective and can be generalized to different video recognition scenarios. In particular, under fully-supervised settings, our approach achieves a top-1 accuracy of 87.1% on Kinectics-400, while using 12 times fewer FLOPs compared with Swin-L and ViViT-H. In zero-shot experiments, our approach surpasses the current state-of-the-art methods by +7.6% and +14.9% in terms of top-1 accuracy under two popular protocols. In few-shot scenarios, our approach outperforms previous best methods by +32.1% and +23.1% when the labeled data is extremely limited. Code and models are available at https://aka.ms/X-CLIP

Minghao Chen, Iro Laina, Andrea Vedaldi

Recent diffusion-based generators can produce high-quality images from textual prompts. However, they often disregard textual instructions that specify the spatial layout of the composition. We propose a simple approach that achieves robust layout control without the need for training or fine-tuning of the image generator. Our technique manipulates the cross-attention layers that the model uses to interface textual and visual information and steers the generation in the desired direction given, e.g., a user-specified layout. To determine how to best guide attention, we study the role of attention maps and explore two alternative strategies, forward and backward guidance. We thoroughly evaluate our approach on three benchmarks and provide several qualitative examples and a comparative analysis of the two strategies that demonstrate the superiority of backward guidance compared to forward guidance, as well as prior work. We further demonstrate the versatility of layout guidance by extending it to applications such as editing the layout and context of real images.

Minghao Chen, Fangyun Wei, Chong Li et al.

Prior works on action representation learning mainly focus on designing various architectures to extract the global representations for short video clips. In contrast, many practical applications such as video alignment have strong demand for learning dense representations for long videos. In this paper, we introduce a novel contrastive action representation learning (CARL) framework to learn frame-wise action representations, especially for long videos, in a self-supervised manner. Concretely, we introduce a simple yet efficient video encoder that considers spatio-temporal context to extract frame-wise representations. Inspired by the recent progress of self-supervised learning, we present a novel sequence contrastive loss (SCL) applied on two correlated views obtained through a series of spatio-temporal data augmentations. SCL optimizes the embedding space by minimizing the KL-divergence between the sequence similarity of two augmented views and a prior Gaussian distribution of timestamp distance. Experiments on FineGym, PennAction and Pouring datasets show that our method outperforms previous state-of-the-art by a large margin for downstream fine-grained action classification. Surprisingly, although without training on paired videos, our approach also shows outstanding performance on video alignment and fine-grained frame retrieval tasks. Code and models are available at https://github.com/minghchen/CARL_code.

Minghao Chen, Zepeng Gao, Shuai Zhao et al.

Unsupervised domain adaptation (UDA) methods facilitate the transfer of models to target domains without labels. However, these methods necessitate a labeled target validation set for hyper-parameter tuning and model selection. In this paper, we aim to find an evaluation metric capable of assessing the quality of a transferred model without access to target validation labels. We begin with the metric based on mutual information of the model prediction. Through empirical analysis, we identify three prevalent issues with this metric: 1) It does not account for the source structure. 2) It can be easily attacked. 3) It fails to detect negative transfer caused by the over-alignment of source and target features. To address the first two issues, we incorporate source accuracy into the metric and employ a new MLP classifier that is held out during training, significantly improving the result. To tackle the final issue, we integrate this enhanced metric with data augmentation, resulting in a novel unsupervised UDA metric called the Augmentation Consistency Metric (ACM). Additionally, we empirically demonstrate the shortcomings of previous experiment settings and conduct large-scale experiments to validate the effectiveness of our proposed metric. Furthermore, we employ our metric to automatically search for the optimal hyper-parameter set, achieving superior performance compared to manually tuned sets across four common benchmarks. Codes will be available soon.

Jianyuan Wang, Minghao Chen, Nikita Karaev et al.

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a step forward in 3D computer vision, where models have typically been constrained to and specialized for single tasks. It is also simple and efficient, reconstructing images in under one second, and still outperforming alternatives that require post-processing with visual geometry optimization techniques. The network achieves state-of-the-art results in multiple 3D tasks, including camera parameter estimation, multi-view depth estimation, dense point cloud reconstruction, and 3D point tracking. We also show that using pretrained VGGT as a feature backbone significantly enhances downstream tasks, such as non-rigid point tracking and feed-forward novel view synthesis. Code and models are publicly available at https://github.com/facebookresearch/vggt.

Stanislaw Szymanowicz, Minghao Chen, Jianyuan Wang et al.

Recent work has shown that neural networks can perform 3D tasks such as Novel View Synthesis (NVS) without explicit 3D reconstruction. Even so, we argue that strong 3D inductive biases are still helpful in the design of such networks. We show this point by introducing LagerNVS, an encoder-decoder neural network for NVS that builds on `3D-aware' latent features. The encoder is initialized from a 3D reconstruction network pre-trained using explicit 3D supervision. This is paired with a lightweight decoder, and trained end-to-end with photometric losses. LagerNVS achieves state-of-the-art deterministic feed-forward Novel View Synthesis (including 31.4 PSNR on Re10k), with and without known cameras, renders in real time, generalizes to in-the-wild data, and can be paired with a diffusion decoder for generative extrapolation.

Minghao Chen, Renbo Tu, Chenxi Huang et al.

Previous work on action representation learning focused on global representations for short video clips. In contrast, many practical applications, such as video alignment, strongly demand learning the intensive representation of long videos. In this paper, we introduce a new framework of contrastive action representation learning (CARL) to learn frame-wise action representation in a self-supervised or weakly-supervised manner, especially for long videos. Specifically, we introduce a simple but effective video encoder that considers both spatial and temporal context by combining convolution and transformer. Inspired by the recent massive progress in self-supervised learning, we propose a new sequence contrast loss (SCL) applied to two related views obtained by expanding a series of spatio-temporal data in two versions. One is the self-supervised version that optimizes embedding space by minimizing KL-divergence between sequence similarity of two augmented views and prior Gaussian distribution of timestamp distance. The other is the weakly-supervised version that builds more sample pairs among videos using video-level labels by dynamic time wrapping (DTW). Experiments on FineGym, PennAction, and Pouring datasets show that our method outperforms previous state-of-the-art by a large margin for downstream fine-grained action classification and even faster inference. Surprisingly, although without training on paired videos like in previous works, our self-supervised version also shows outstanding performance in video alignment and fine-grained frame retrieval tasks.

Yuqi Lin, Minghao Chen, Kaipeng Zhang et al.

Contrastive Language-Image Pre-training (CLIP) has demonstrated impressive capabilities in open-vocabulary classification. The class token in the image encoder is trained to capture the global features to distinguish different text descriptions supervised by contrastive loss, making it highly effective for single-label classification. However, it shows poor performance on multi-label datasets because the global feature tends to be dominated by the most prominent class and the contrastive nature of softmax operation aggravates it. In this study, we observe that the multi-label classification results heavily rely on discriminative local features but are overlooked by CLIP. As a result, we dissect the preservation of patch-wise spatial information in CLIP and proposed a local-to-global framework to obtain image tags. It comprises three steps: (1) patch-level classification to obtain coarse scores; (2) dual-masking attention refinement (DMAR) module to refine the coarse scores; (3) class-wise reidentification (CWR) module to remedy predictions from a global perspective. This framework is solely based on frozen CLIP and significantly enhances its multi-label classification performance on various benchmarks without dataset-specific training. Besides, to comprehensively assess the quality and practicality of generated tags, we extend their application to the downstream task, i.e., weakly supervised semantic segmentation (WSSS) with generated tags as image-level pseudo labels. Experiments demonstrate that this classify-then-segment paradigm dramatically outperforms other annotation-free segmentation methods and validates the effectiveness of generated tags. Our code is available at https://github.com/linyq2117/TagCLIP.

Minghao Chen, Xinyi Hu, Zhou Yu et al.

Large Language Model (LLM) based agents have demonstrated proficiency in multi-step interactions with graphical user interfaces (GUIs). While most research focuses on improving single-task performance, practical scenarios often involve repetitive GUI tasks for which invoking LLM reasoning repeatedly, i.e., the ReAct paradigm, is inefficient. Prior to LLMs, traditional Robotic Process Automation (RPA) offers runtime efficiency but demands significant manual effort to develop and maintain. To bridge this gap, we propose AutoRPA, a framework that automatically distills the decision logic of ReAct-style agents into robust RPA functions. AutoRPA introduces two core innovations: (1) A translator-builder pipeline, where a translator agent converts hard-coded ReAct actions into soft-coded procedures, and a builder agent synthesizes robust RPA functions via retrieval-augmented generation over multiple trajectories; (2) A hybrid repair strategy during code verification, combining RPA execution with ReAct-based fallback for iterative refinement. Experiments across multiple GUI environments demonstrate that RPA functions generated by AutoRPA successfully solve similar tasks while reducing token usage by 82% to 96%, significantly improving runtime efficiency and reusability.

Yanting Yang, Minghao Chen, Qibo Qiu et al.

For a general-purpose robot to operate in reality, executing a broad range of instructions across various environments is imperative. Central to the reinforcement learning and planning for such robotic agents is a generalizable reward function. Recent advances in vision-language models, such as CLIP, have shown remarkable performance in the domain of deep learning, paving the way for open-domain visual recognition. However, collecting data on robots executing various language instructions across multiple environments remains a challenge. This paper aims to transfer video-language models with robust generalization into a generalizable language-conditioned reward function, only utilizing robot video data from a minimal amount of tasks in a singular environment. Unlike common robotic datasets used for training reward functions, human video-language datasets rarely contain trivial failure videos. To enhance the model's ability to distinguish between successful and failed robot executions, we cluster failure video features to enable the model to identify patterns within. For each cluster, we integrate a newly trained failure prompt into the text encoder to represent the corresponding failure mode. Our language-conditioned reward function shows outstanding generalization to new environments and new instructions for robot planning and reinforcement learning.

Xinheng Li, Minghao Chen, Mengqing Wu et al.

Single image dehazing is often constrained by a trade-off between restoration quality and computational efficiency. While efficient, CNN networks struggle to learn robust priors for dense and non-homogeneous haze. Conversely, diffusion models provide strong generative priors but suffer from severe inference latency and sampling instability. To address these limitations, we propose ZID-Net, a novel framework that explicitly decouples diffusion supervision from feed-forward inference. For efficient inference, we design a frequency-spatial decoupled feed-forward backbone. Within this backbone, a Channel-Spatial Laplacian Mask (CSLM) filters haze-amplified noise to extract purified structural details, while Lightweight Global Context Blocks (LGCBs) establish long-range spatial dependencies to capture the global variations of haze. A Dynamic Feature Arbitration Block (DFAB) then adaptively fuses these semantic and structural features for robust reconstruction. To provide this backbone with physical priors without the inference cost, we introduce a Zero-Inference Prior Propagation Head (ZI-PPH) during training. ZI-PPH leverages a conditional diffusion process to predict residual noise, providing degradation-aware structural supervision to the backbone. By discarding the diffusion branch at test time, ZID-Net integrates diffusion priors into a pure feed-forward architecture for accurate and efficient restoration. ZID-Net achieves 40.75 dB PSNR on the synthetic RESIDE dataset and outperforms existing methods with a 1.13 dB gain on real-world datasets. Additionally, it yields a 3.06 dB PSNR gain on the StateHaze1k remote sensing dataset with an inference time of just 19.35 ms. The project code is available at: https://github.com/XoomitLXH/ZID-Net.

Zhanwei Zhang, Minghao Chen, Shuai Xiao et al.

Recent self-training techniques have shown notable improvements in unsupervised domain adaptation for 3D object detection (3D UDA). These techniques typically select pseudo labels, i.e., 3D boxes, to supervise models for the target domain. However, this selection process inevitably introduces unreliable 3D boxes, in which 3D points cannot be definitively assigned as foreground or background. Previous techniques mitigate this by reweighting these boxes as pseudo labels, but these boxes can still poison the training process. To resolve this problem, in this paper, we propose a novel pseudo label refinery framework. Specifically, in the selection process, to improve the reliability of pseudo boxes, we propose a complementary augmentation strategy. This strategy involves either removing all points within an unreliable box or replacing it with a high-confidence box. Moreover, the point numbers of instances in high-beam datasets are considerably higher than those in low-beam datasets, also degrading the quality of pseudo labels during the training process. We alleviate this issue by generating additional proposals and aligning RoI features across different domains. Experimental results demonstrate that our method effectively enhances the quality of pseudo labels and consistently surpasses the state-of-the-art methods on six autonomous driving benchmarks. Code will be available at https://github.com/Zhanwei-Z/PERE.

Zhanwei Zhang, Zishuo Hua, Minghao Chen et al.

Predicting future trajectories of traffic agents accurately holds substantial importance in various applications such as autonomous driving. Previous methods commonly infer all future steps of an agent either recursively or simultaneously. However, the recursive strategy suffers from the accumulated error, while the simultaneous strategy overlooks the constraints among future steps, resulting in kinematically infeasible predictions. To address these issues, in this paper, we propose G2LTraj, a plug-and-play global-to-local generation approach for trajectory prediction. Specifically, we generate a series of global key steps that uniformly cover the entire future time range. Subsequently, the local intermediate steps between the adjacent key steps are recursively filled in. In this way, we prevent the accumulated error from propagating beyond the adjacent key steps. Moreover, to boost the kinematical feasibility, we not only introduce the spatial constraints among key steps but also strengthen the temporal constraints among the intermediate steps. Finally, to ensure the optimal granularity of key steps, we design a selectable granularity strategy that caters to each predicted trajectory. Our G2LTraj significantly improves the performance of seven existing trajectory predictors across the ETH, UCY and nuScenes datasets. Experimental results demonstrate its effectiveness. Code will be available at https://github.com/Zhanwei-Z/G2LTraj.

Zhuangzhe Wu, Yue Xin, Chengkai Hou et al.

Articulated objects are fundamental for robotics, simulation of physics, and interactive virtual environments. However, reconstructing them from visual input remains challenging, as it requires jointly inferring both part geometry and kinematic structure. We present, an end-to-end autoregressive framework that directly generates executable articulated object models from visual observations. Given image and object-level 3D cues, our method sequentially produces part geometries and their associated joint parameters, resulting in complete URDF models without reliance on multi-stage pipelines. The generation proceeds until the model determines that all parts have been produced, automatically inferring complete geometry and kinematics. Building on this capability, we enable a new Real-Follow-Sim paradigm, where high-fidelity digital twins constructed from visual observations allow policies trained and tested purely in simulation to transfer to real robots without online adaptation. Experiments on large-scale articulated object benchmarks and real-world robotic tasks demonstrate that outperforms prior methods in geometric reconstruction quality, joint parameter accuracy, and physical executability.

Jianyuan Wang, Minghao Chen, Shangzhan Zhang et al.

Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features useful for other tasks. Here, we show that the quality of these models scales predictably with model and data size. We do so by introducing VGGT-$Ω$, which substantially improves reconstruction accuracy, efficiency, and capabilities for both static and dynamic scenes. To enable training this model at an unprecedented scale, we introduce architectural changes that improve training efficiency, a high-quality data annotation pipeline that supports dynamic scenes, and a self-supervised learning protocol. We simplify VGGT's architecture by using a single dense prediction head with multi-task supervision and removing the expensive high-resolution convolutional layers. We also use registers to aggregate scene information into a compact representation and introduce register attention, which restricts inter-frame information exchange to these registers, in part replacing global attention. In this way, during training, VGGT-$Ω$ uses only about 30% of the GPU memory of its predecessor, allowing us to train with 15x more supervised data than prior work and to leverage vast amounts of unlabeled video data. VGGT-$Ω$ achieves strong results for reconstruction of static and dynamic scenes across multiple benchmarks, for example, improving over the previous best camera estimation accuracy on Sintel by 77%. We also show that the learned registers can improve vision-language-action models and support alignment with language, suggesting that reconstruction can be a powerful and scalable proxy task for spatial understanding. Project Page: http://vggt-omega.github.io/

Honghui Yang, Wenxiao Wang, Minghao Chen et al.

Recent Transformer-based 3D object detectors learn point cloud features either from point- or voxel-based representations. However, the former requires time-consuming sampling while the latter introduces quantization errors. In this paper, we present a novel Point-Voxel Transformer for single-stage 3D detection (PVT-SSD) that takes advantage of these two representations. Specifically, we first use voxel-based sparse convolutions for efficient feature encoding. Then, we propose a Point-Voxel Transformer (PVT) module that obtains long-range contexts in a cheap manner from voxels while attaining accurate positions from points. The key to associating the two different representations is our introduced input-dependent Query Initialization module, which could efficiently generate reference points and content queries. Then, PVT adaptively fuses long-range contextual and local geometric information around reference points into content queries. Further, to quickly find the neighboring points of reference points, we design the Virtual Range Image module, which generalizes the native range image to multi-sensor and multi-frame. The experiments on several autonomous driving benchmarks verify the effectiveness and efficiency of the proposed method. Code will be available at https://github.com/Nightmare-n/PVT-SSD.

Minghao Chen, Kan Wu, Bolin Ni et al.

Vision Transformer has shown great visual representation power in substantial vision tasks such as recognition and detection, and thus been attracting fast-growing efforts on manually designing more effective architectures. In this paper, we propose to use neural architecture search to automate this process, by searching not only the architecture but also the search space. The central idea is to gradually evolve different search dimensions guided by their E-T Error computed using a weight-sharing supernet. Moreover, we provide design guidelines of general vision transformers with extensive analysis according to the space searching process, which could promote the understanding of vision transformer. Remarkably, the searched models, named S3 (short for Searching the Search Space), from the searched space achieve superior performance to recently proposed models, such as Swin, DeiT and ViT, when evaluated on ImageNet. The effectiveness of S3 is also illustrated on object detection, semantic segmentation and visual question answering, demonstrating its generality to downstream vision and vision-language tasks. Code and models will be available at https://github.com/microsoft/Cream.

Kan Wu, Houwen Peng, Minghao Chen et al.

Relative position encoding (RPE) is important for transformer to capture sequence ordering of input tokens. General efficacy has been proven in natural language processing. However, in computer vision, its efficacy is not well studied and even remains controversial, e.g., whether relative position encoding can work equally well as absolute position? In order to clarify this, we first review existing relative position encoding methods and analyze their pros and cons when applied in vision transformers. We then propose new relative position encoding methods dedicated to 2D images, called image RPE (iRPE). Our methods consider directional relative distance modeling as well as the interactions between queries and relative position embeddings in self-attention mechanism. The proposed iRPE methods are simple and lightweight. They can be easily plugged into transformer blocks. Experiments demonstrate that solely due to the proposed encoding methods, DeiT and DETR obtain up to 1.5% (top-1 Acc) and 1.3% (mAP) stable improvements over their original versions on ImageNet and COCO respectively, without tuning any extra hyperparameters such as learning rate and weight decay. Our ablation and analysis also yield interesting findings, some of which run counter to previous understanding. Code and models are open-sourced at https://github.com/microsoft/Cream/tree/main/iRPE.

Minghao Chen, Houwen Peng, Jianlong Fu et al.

Recently, pure transformer-based models have shown great potentials for vision tasks such as image classification and detection. However, the design of transformer networks is challenging. It has been observed that the depth, embedding dimension, and number of heads can largely affect the performance of vision transformers. Previous models configure these dimensions based upon manual crafting. In this work, we propose a new one-shot architecture search framework, namely AutoFormer, dedicated to vision transformer search. AutoFormer entangles the weights of different blocks in the same layers during supernet training. Benefiting from the strategy, the trained supernet allows thousands of subnets to be very well-trained. Specifically, the performance of these subnets with weights inherited from the supernet is comparable to those retrained from scratch. Besides, the searched models, which we refer to AutoFormers, surpass the recent state-of-the-arts such as ViT and DeiT. In particular, AutoFormer-tiny/small/base achieve 74.7%/81.7%/82.4% top-1 accuracy on ImageNet with 5.7M/22.9M/53.7M parameters, respectively. Lastly, we verify the transferability of AutoFormer by providing the performance on downstream benchmarks and distillation experiments. Code and models are available at https://github.com/microsoft/AutoML.

Chulin Xie, Minghao Chen, Pin-Yu Chen et al.

Federated Learning (FL) as a distributed learning paradigm that aggregates information from diverse clients to train a shared global model, has demonstrated great success. However, malicious clients can perform poisoning attacks and model replacement to introduce backdoors into the trained global model. Although there have been intensive studies designing robust aggregation methods and empirical robust federated training protocols against backdoors, existing approaches lack robustness certification. This paper provides the first general framework, Certifiably Robust Federated Learning (CRFL), to train certifiably robust FL models against backdoors. Our method exploits clipping and smoothing on model parameters to control the global model smoothness, which yields a sample-wise robustness certification on backdoors with limited magnitude. Our certification also specifies the relation to federated learning parameters, such as poisoning ratio on instance level, number of attackers, and training iterations. Practically, we conduct comprehensive experiments across a range of federated datasets, and provide the first benchmark for certified robustness against backdoor attacks in federated learning. Our code is available at https://github.com/AI-secure/CRFL.

Minghao Chen, Houwen Peng, Jianlong Fu et al.

Despite remarkable progress achieved, most neural architecture search (NAS) methods focus on searching for one single accurate and robust architecture. To further build models with better generalization capability and performance, model ensemble is usually adopted and performs better than stand-alone models. Inspired by the merits of model ensemble, we propose to search for multiple diverse models simultaneously as an alternative way to find powerful models. Searching for ensembles is non-trivial and has two key challenges: enlarged search space and potentially more complexity for the searched model. In this paper, we propose a one-shot neural ensemble architecture search (NEAS) solution that addresses the two challenges. For the first challenge, we introduce a novel diversity-based metric to guide search space shrinking, considering both the potentiality and diversity of candidate operators. For the second challenge, we enable a new search dimension to learn layer sharing among different models for efficiency purposes. The experiments on ImageNet clearly demonstrate that our solution can improve the supernet's capacity of ranking ensemble architectures, and further lead to better search results. The discovered architectures achieve superior performance compared with state-of-the-arts such as MobileNetV3 and EfficientNet families under aligned settings. Moreover, we evaluate the generalization ability and robustness of our searched architecture on the COCO detection benchmark and achieve a 3.1% improvement on AP compared with MobileNetV3. Codes and models are available at https://github.com/researchmm/NEAS.

Zili Liu, Guodong Xu, Honghui Yang et al.

3D object detector based on Hough voting achieves great success and derives many follow-up works. Despite constantly refreshing the detection accuracy, these works suffer from handcrafted components used to eliminate redundant boxes, and thus are non-end-to-end and time-consuming. In this work, we propose a suppress-and-refine framework to remove these handcrafted components. To fully utilize full-resolution information and achieve real-time speed, it directly consumes feature points and redundant 3D proposals. Specifically, it first suppresses noisy 3D feature points and then feeds them to 3D proposals for the following RoI-aware refinement. With the gating mechanism to build fine proposal features and the self-attention mechanism to model relationships, our method can produce high-quality predictions with a small computation budget in an end-to-end manner. To this end, we present the first fully end-to-end 3D detector, SRDet, on the basis of VoteNet. It achieves state-of-the-art performance on the challenging ScanNetV2 and SUN RGB-D datasets with the fastest speed ever. Our code will be available at https://github.com/ZJULearning/SRDet.

Jia Guo, Minghao Chen, Yao Hu et al.

Knowledge distillation aims at obtaining a compact and effective model by learning the mapping function from a much larger one. Due to the limited capacity of the student, the student would underfit the teacher. Therefore, student performance would unexpectedly drop when distilling from an oversized teacher, termed the capacity gap problem. We investigate this problem by study the gap of confidence between teacher and student. We find that the magnitude of confidence is not necessary for knowledge distillation and could harm the student performance if the student are forced to learn confidence. We propose Spherical Knowledge Distillation to eliminate this gap explicitly, which eases the underfitting problem. We find this novel knowledge representation can improve compact models with much larger teachers and is robust to temperature. We conducted experiments on both CIFAR100 and ImageNet, and achieve significant improvement. Specifically, we train ResNet18 to 73.0 accuracy, which is a substantial improvement over previous SOTA and is on par with resnet34 almost twice the student size. The implementation has been shared at https://github.com/forjiuzhou/Spherical-Knowledge-Distillation.

Minghao Chen, Shuai Zhao, Haifeng Liu et al.

Recently, remarkable progress has been made in learning transferable representation across domains. Previous works in domain adaptation are majorly based on two techniques: domain-adversarial learning and self-training. However, domain-adversarial learning only aligns feature distributions between domains but does not consider whether the target features are discriminative. On the other hand, self-training utilizes the model predictions to enhance the discrimination of target features, but it is unable to explicitly align domain distributions. In order to combine the strengths of these two methods, we propose a novel method called Adversarial-Learned Loss for Domain Adaptation (ALDA). We first analyze the pseudo-label method, a typical self-training method. Nevertheless, there is a gap between pseudo-labels and the ground truth, which can cause incorrect training. Thus we introduce the confusion matrix, which is learned through an adversarial manner in ALDA, to reduce the gap and align the feature distributions. Finally, a new loss function is auto-constructed from the learned confusion matrix, which serves as the loss for unlabeled target samples. Our ALDA outperforms state-of-the-art approaches in four standard domain adaptation datasets. Our code is available at https://github.com/ZJULearning/ALDA.

Minghao Chen, Iro Laina, Andrea Vedaldi

We consider the problem of editing 3D objects and scenes based on open-ended language instructions. A common approach to this problem is to use a 2D image generator or editor to guide the 3D editing process, obviating the need for 3D data. However, this process is often inefficient due to the need for iterative updates of costly 3D representations, such as neural radiance fields, either through individual view edits or score distillation sampling. A major disadvantage of this approach is the slow convergence caused by aggregating inconsistent information across views, as the guidance from 2D models is not multi-view consistent. We thus introduce the Direct Gaussian Editor (DGE), a method that addresses these issues in two stages. First, we modify a given high-quality image editor like InstructPix2Pix to be multi-view consistent. To do so, we propose a training-free approach that integrates cues from the 3D geometry of the underlying scene. Second, given a multi-view consistent edited sequence of images, we directly and efficiently optimize the 3D representation, which is based on 3D Gaussian Splatting. Because it avoids incremental and iterative edits, DGE is significantly more accurate and efficient than existing approaches and offers additional benefits, such as enabling selective editing of parts of the scene.

Changyue Shi, Chuxiao Yang, Xinyuan Hu et al.

Dynamic Gaussian Splatting approaches have achieved remarkable performance for 4D scene reconstruction. However, these approaches rely on dense-frame video sequences for photorealistic reconstruction. In real-world scenarios, due to equipment constraints, sometimes only sparse frames are accessible. In this paper, we propose Sparse4DGS, the first method for sparse-frame dynamic scene reconstruction. We observe that dynamic reconstruction methods fail in both canonical and deformed spaces under sparse-frame settings, especially in areas with high texture richness. Sparse4DGS tackles this challenge by focusing on texture-rich areas. For the deformation network, we propose Texture-Aware Deformation Regularization, which introduces a texture-based depth alignment loss to regulate Gaussian deformation. For the canonical Gaussian field, we introduce Texture-Aware Canonical Optimization, which incorporates texture-based noise into the gradient descent process of canonical Gaussians. Extensive experiments show that when taking sparse frames as inputs, our method outperforms existing dynamic or few-shot techniques on NeRF-Synthetic, HyperNeRF, NeRF-DS, and our iPhone-4D datasets.

Minghao Chen, Roman Shapovalov, Iro Laina et al. · meta-ai

Text- or image-to-3D generators and 3D scanners can now produce 3D assets with high-quality shapes and textures. These assets typically consist of a single, fused representation, like an implicit neural field, a Gaussian mixture, or a mesh, without any useful structure. However, most applications and creative workflows require assets to be made of several meaningful parts that can be manipulated independently. To address this gap, we introduce PartGen, a novel approach that generates 3D objects composed of meaningful parts starting from text, an image, or an unstructured 3D object. First, given multiple views of a 3D object, generated or rendered, a multi-view diffusion model extracts a set of plausible and view-consistent part segmentations, dividing the object into parts. Then, a second multi-view diffusion model takes each part separately, fills in the occlusions, and uses those completed views for 3D reconstruction by feeding them to a 3D reconstruction network. This completion process considers the context of the entire object to ensure that the parts integrate cohesively. The generative completion model can make up for the information missing due to occlusions; in extreme cases, it can hallucinate entirely invisible parts based on the input 3D asset. We evaluate our method on generated and real 3D assets and show that it outperforms segmentation and part-extraction baselines by a large margin. We also showcase downstream applications such as 3D part editing.

Minghao Chen, Junyu Xie, Iro Laina et al.

We propose a novel feed-forward 3D editing framework called Shap-Editor. Prior research on editing 3D objects primarily concentrated on editing individual objects by leveraging off-the-shelf 2D image editing networks. This is achieved via a process called distillation, which transfers knowledge from the 2D network to 3D assets. Distillation necessitates at least tens of minutes per asset to attain satisfactory editing results, and is thus not very practical. In contrast, we ask whether 3D editing can be carried out directly by a feed-forward network, eschewing test-time optimisation. In particular, we hypothesise that editing can be greatly simplified by first encoding 3D objects in a suitable latent space. We validate this hypothesis by building upon the latent space of Shap-E. We demonstrate that direct 3D editing in this space is possible and efficient by building a feed-forward editor network that only requires approximately one second per edit. Our experiments show that Shap-Editor generalises well to both in-distribution and out-of-distribution 3D assets with different prompts, exhibiting comparable performance with methods that carry out test-time optimisation for each edited instance.

Xinyuan Hu, Changyue Shi, Chuxiao Yang et al.

Feed-forward 3D reconstruction from sparse, low-resolution (LR) images is a crucial capability for real-world applications, such as autonomous driving and embodied AI. However, existing methods often fail to recover fine texture details. This limitation stems from the inherent lack of high-frequency information in LR inputs. To address this, we propose \textbf{SRSplat}, a feed-forward framework that reconstructs high-resolution 3D scenes from only a few LR views. Our main insight is to compensate for the deficiency of texture information by jointly leveraging external high-quality reference images and internal texture cues. We first construct a scene-specific reference gallery, generated for each scene using Multimodal Large Language Models (MLLMs) and diffusion models. To integrate this external information, we introduce the \textit{Reference-Guided Feature Enhancement (RGFE)} module, which aligns and fuses features from the LR input images and their reference twin image. Subsequently, we train a decoder to predict the Gaussian primitives using the multi-view fused feature obtained from \textit{RGFE}. To further refine predicted Gaussian primitives, we introduce \textit{Texture-Aware Density Control (TADC)}, which adaptively adjusts Gaussian density based on the internal texture richness of the LR inputs. Extensive experiments demonstrate that our SRSplat outperforms existing methods on various datasets, including RealEstate10K, ACID, and DTU, and exhibits strong cross-dataset and cross-resolution generalization capabilities.

Yufei Yin, Jie Zheng, Qianke Meng et al.

Zero-shot 3D Visual Grounding (3DVG) is a critical capability for open-world embodied AI. However, existing methods are fundamentally bottlenecked by the poor quality of open-vocabulary 3D proposals, suffering from inaccurate categories and imprecise geometries, as well as the spatial redundancy of exhaustive multi-view reasoning. To address these challenges, we propose MCM-VG, a novel framework that achieves robust zero-shot 3DVG by explicitly establishing Multiple Consistent 2D-3D Mappings. Instead of passively relying on noisy 3D segments, MCM-VG enforces 2D-3D consistency across three fundamental dimensions to achieve precise target localization and reliable reasoning. First, a Semantic Alignment module corrects category mismatches via LLM-driven query parsing and coarse-to-fine 2D-3D matching. Second, an Instance Rectification module leverages VLM-guided 2D segmentations to reconstruct missing targets, back-projecting these reliable visual priors to establish accurate 3D geometries. Finally, to eliminate spatial redundancy, a Viewpoint Distillation module clusters 3D camera directions to extract optimal frames. By pairing these optimal RGB frames with Bird's Eye View maps into concise visual prompt sets, we formulate the final target disambiguation as a multiple-choice reasoning task for Vision-Language Models. Extensive evaluations on ScanRefer and Nr3D benchmarks demonstrate that MCM-VG sets a new state-of-the-art for zero-shot 3D visual grounding. Remarkably, it achieves 62.0\% and 53.6\% in Acc@0.25 and Acc@0.5 on ScanRefer, outperforming previous baselines by substantial margins of 6.4\% and 4.0\%.

Minghao Chen, Jianyuan Wang, Roman Shapovalov et al. · meta-ai

We introduce AutoPartGen, a model that generates objects composed of 3D parts in an autoregressive manner. This model can take as input an image of an object, 2D masks of the object's parts, or an existing 3D object, and generate a corresponding compositional 3D reconstruction. Our approach builds upon 3DShape2VecSet, a recent latent 3D representation with powerful geometric expressiveness. We observe that this latent space exhibits strong compositional properties, making it particularly well-suited for part-based generation tasks. Specifically, AutoPartGen generates object parts autoregressively, predicting one part at a time while conditioning on previously generated parts and additional inputs, such as 2D images, masks, or 3D objects. This process continues until the model decides that all parts have been generated, thus determining automatically the type and number of parts. The resulting parts can be seamlessly assembled into coherent objects or scenes without requiring additional optimization. We evaluate both the overall 3D generation capabilities and the part-level generation quality of AutoPartGen, demonstrating that it achieves state-of-the-art performance in 3D part generation.

Zhipeng Wei, Kuo Cai, Junda She et al.

Local life service is a vital scenario in Kuaishou App, where video recommendation is intrinsically linked with store's location information. Thus, recommendation in our scenario is challenging because we should take into account user's interest and real-time location at the same time. In the face of such complex scenarios, end-to-end generative recommendation has emerged as a new paradigm, such as OneRec in the short video scenario, OneSug in the search scenario, and EGA in the advertising scenario. However, in local life service, an end-to-end generative recommendation model has not yet been developed as there are some key challenges to be solved. The first challenge is how to make full use of geographic information. The second challenge is how to balance multiple objectives, including user interests, the distance between user and stores, and some other business objectives. To address the challenges, we propose OneLoc. Specifically, we leverage geographic information from different perspectives: (1) geo-aware semantic ID incorporates both video and geographic information for tokenization, (2) geo-aware self-attention in the encoder leverages both video location similarity and user's real-time location, and (3) neighbor-aware prompt captures rich context information surrounding users for generation. To balance multiple objectives, we use reinforcement learning and propose two reward functions, i.e., geographic reward and GMV reward. With the above design, OneLoc achieves outstanding offline and online performance. In fact, OneLoc has been deployed in local life service of Kuaishou App. It serves 400 million active users daily, achieving 21.016% and 17.891% improvements in terms of gross merchandise value (GMV) and orders numbers.

Yunnan Wang, Kecheng Zheng, Jianyuan Wang et al.

The convergence of 3D geometric perception and video synthesis has created an unprecedented demand for large-scale video data that is rich in both semantic and spatio-temporal information. While existing datasets have advanced either 3D understanding or video generation, a significant gap remains in providing a unified resource that supports both domains at scale. To bridge this chasm, we introduce SceneScribe-1M, a new large-scale, multi-modal video dataset. It comprises one million in-the-wild videos, each meticulously annotated with detailed textual descriptions, precise camera parameters, dense depth maps, and consistent 3D point tracks. We demonstrate the versatility and value of SceneScribe-1M by establishing benchmarks across a wide array of downstream tasks, including monocular depth estimation, scene reconstruction, and dynamic point tracking, as well as generative tasks such as text-to-video synthesis, with or without camera control. By open-sourcing SceneScribe-1M, we aim to provide a comprehensive benchmark and a catalyst for research, fostering the development of models that can both perceive the dynamic 3D world and generate controllable, realistic video content.

Jiatong Bai, Minghao Chen, Wankai Tang et al.

Most existing DOA estimation methods assume ideal source incident angles with minimal noise. Moreover, directly using pre-estimated angles to calculate weighted coefficients can lead to performance loss. Thus, a green multi-modal (MM) fusion DOA framework is proposed to realize a more practical, low-cost and high time-efficiency DOA estimation for a H$^2$AD array. Firstly, two more efficient clustering methods, global maximum cos\_similarity clustering (GMaxCS) and global minimum distance clustering (GMinD), are presented to infer more precise true solutions from the candidate solution sets. Based on this, an iteration weighted fusion (IWF)-based method is introduced to iteratively update weighted fusion coefficients and the clustering center of the true solution classes by using the estimated values. Particularly, the coarse DOA calculated by fully digital (FD) subarray, serves as the initial cluster center. The above process yields two methods called MM-IWF-GMaxCS and MM-IWF-GMinD. To further provide a higher-accuracy DOA estimation, a fusion network (fusionNet) is proposed to aggregate the inferred two-part true angles and thus generates two effective approaches called MM-fusionNet-GMaxCS and MM-fusionNet-GMinD. The simulation outcomes show the proposed four approaches can achieve the ideal DOA performance and the CRLB. Meanwhile, proposed MM-fusionNet-GMaxCS and MM-fusionNet-GMinD exhibit superior DOA performance compared to MM-IWF-GMaxCS and MM-IWF-GMinD, especially in extremely-low SNR range.

Changyue Shi, Minghao Chen, Yiping Mao et al.

Bridging the gap between complex human instructions and precise 3D object grounding remains a significant challenge in vision and robotics. Existing 3D segmentation methods often struggle to interpret ambiguous, reasoning-based instructions, while 2D vision-language models that excel at such reasoning lack intrinsic 3D spatial understanding. In this paper, we introduce REALM, an innovative MLLM-agent framework that enables open-world reasoning-based segmentation without requiring extensive 3D-specific post-training. We perform segmentation directly on 3D Gaussian Splatting representations, capitalizing on their ability to render photorealistic novel views that are highly suitable for MLLM comprehension. As directly feeding one or more rendered views to the MLLM can lead to high sensitivity to viewpoint selection, we propose a novel Global-to-Local Spatial Grounding strategy. Specifically, multiple global views are first fed into the MLLM agent in parallel for coarse-level localization, aggregating responses to robustly identify the target object. Then, several close-up novel views of the object are synthesized to perform fine-grained local segmentation, yielding accurate and consistent 3D masks. Extensive experiments show that REALM achieves remarkable performance in interpreting both explicit and implicit instructions across LERF, 3D-OVS, and our newly introduced REALM3D benchmarks. Furthermore, our agent framework seamlessly supports a range of 3D interaction tasks, including object removal, replacement, and style transfer, demonstrating its practical utility and versatility. Project page: https://ChangyueShi.github.io/REALM.

Yuhao Du, Qianwei Huang, Guo Zhu et al.

The rapid advancement of speech-to-speech (S2S) large language models (LLMs) has significantly improved real-time spoken interaction. However, current evaluation frameworks remain inadequate for assessing performance in complex, multi-turn dialogues. To address this, we introduce MTalk-Bench, a multi-turn S2S benchmark covering three core dimensions: Semantic Information, Paralinguistic Information, and Ambient Sound. Each dimension includes nine realistic scenarios, along with targeted tasks to assess specific capabilities such as reasoning. Our dual-method evaluation framework combines Arena-style evaluation (pairwise comparison) and Rubrics-based evaluation (absolute scoring) for relative and absolute assessment. The benchmark includes both model and human outputs, evaluated by human evaluators and LLMs. Experimental results reveal two sets of findings. Overall performance of S2S LLMs: (1) models excel at semantic information processing yet underperform on paralinguistic information and ambient sounds perception; (2) models typically regain coherence by increasing response length, sacrificing efficiency in multi-turn dialogues; (3) modality-aware, task-specific designs outperform brute scaling. Evaluation framework and reliability: (1) Arena and Rubrics yield consistent, complementary rankings, but reliable distinctions emerge only when performance gaps are large; (2) LLM-as-a-judge aligns with humans when gaps are clear or criteria explicit, but exhibits position and length biases and is reliable on nonverbal evaluation only with text annotations. These results highlight current limitations in S2S evaluation and the need for more robust, speech-aware assessment frameworks.

Yufei Yin, Yuchen Xing, Qianke Meng et al.

Understanding long videos requires extracting query-relevant information from long sequences under tight compute budgets. Existing text-then-LLM pipelines lose fine-grained visual cues, while video-based multimodal large language models (MLLMs) can keep visual details but are too frame-hungry and computationally expensive. In this work, we aim to harness MLLMs for efficient video understanding. We propose ProVCA, a progressive video condensation agent that iteratively locates key video frames at multiple granularities. ProVCA first adopts a segment localization module to identify the video segment relevant to the query, then a snippet selection module to select important snippets based on similarity, and finally a keyframe refinement module to pinpoint specific keyframes in those snippets. By progressively narrowing the scope from coarse segments to fine frames, ProVCA identifies a small set of keyframes for MLLM-based reasoning. ProVCA achieves state-of-the-art zero-shot accuracies of 69.3\% on EgoSchema, 80.5\% on NExT-QA, and 77.7\% on IntentQA, while using fewer frames than previous training-free methods.

Minghao Chen

With the rapid advancement of technology, the recognition of underwater acoustic signals in complex environments has become increasingly crucial. Currently, mainstream underwater acoustic signal recognition relies primarily on time-frequency analysis to extract spectral features, finding widespread applications in the field. However, existing recognition methods heavily depend on expert systems, facing limitations such as restricted knowledge bases and challenges in handling complex relationships. These limitations stem from the complexity and maintenance difficulties associated with rules or inference engines. Recognizing the potential advantages of deep learning in handling intricate relationships, this paper proposes a method utilizing neural networks for underwater acoustic signal recognition. The proposed approach involves continual learning of features extracted from spectra for the classification of underwater acoustic signals. Deep learning models can automatically learn abstract features from data and continually adjust weights during training to enhance classification performance.

Yufei Yin, Qianke Meng, Minghao Chen et al.

Long-form video understanding remains challenging due to the extended temporal structure and dense multimodal cues. Despite recent progress, many existing approaches still rely on hand-crafted reasoning pipelines or employ token-consuming video preprocessing to guide MLLMs in autonomous reasoning. To overcome these limitations, we introduce VideoARM, an Agentic Reasoning-over-hierarchical-Memory paradigm for long-form video understanding. Instead of static, exhaustive preprocessing, VideoARM performs adaptive, on-the-fly agentic reasoning and memory construction. Specifically, VideoARM performs an adaptive and continuous loop of observing, thinking, acting, and memorizing, where a controller autonomously invokes tools to interpret the video in a coarse-to-fine manner, thereby substantially reducing token consumption. In parallel, a hierarchical multimodal memory continuously captures and updates multi-level clues throughout the operation of the agent, providing precise contextual information to support the controller in decision-making. Experiments on prevalent benchmarks demonstrate that VideoARM outperforms the state-of-the-art method, DVD, while significantly reducing token consumption for long-form videos.

Saman Motamed, Minghao Chen, Luc Van Gool et al.

Despite impressive visual fidelity, modern video generative models frequently produce sequences that violate intuitive physical laws, such as objects floating, teleporting, or morphing in ways that defy causality. While humans can easily detect such implausibilities, there remains no robust method for quantitatively assessing physical realism in video. In this work, we explore whether Video-Language Models (VLMs) can be trained to serve as reliable judges of physical plausibility. We find that existing VLMs struggle to identify physics violations, exposing fundamental limitations in their temporal and causal reasoning. To address this, we introduce TRAVL, a fine-tuning recipe that combines a balanced training dataset with a trajectory-aware attention module to improve motion encoding and discrimination in VLMs. To evaluate physical reasoning more rigorously, we propose ImplausiBench, a benchmark of 300 videos (150 real, 150 generated) that removes linguistic biases and isolates visual-temporal understanding. Performance is reported both with gold-standard human judgments and stricter LLM-as-judge metrics. Together, TRAVL and ImplausiBench offer a unified framework for probing and improving physical plausibility in multimodal models, shedding light on a challenging and underexplored aspect of visual-temporal understanding.

Hao Fang, Daoxin Zhang, Yi Zhang et al.

Instance segmentation can detect where the objects are in an image, but hard to understand the relationship between them. We pay attention to a typical relationship, relative saliency. A closely related task, salient object detection, predicts a binary map highlighting a visually salient region while hard to distinguish multiple objects. Directly combining two tasks by post-processing also leads to poor performance. There is a lack of research on relative saliency at present, limiting the practical applications such as content-aware image cropping, video summary, and image labeling. In this paper, we study the Salient Object Ranking (SOR) task, which manages to assign a ranking order of each detected object according to its visual saliency. We propose the first end-to-end framework of the SOR task and solve it in a multi-task learning fashion. The framework handles instance segmentation and salient object ranking simultaneously. In this framework, the SOR branch is independent and flexible to cooperate with different detection methods, so that easy to use as a plugin. We also introduce a Position-Preserved Attention (PPA) module tailored for the SOR branch. It consists of the position embedding stage and feature interaction stage. Considering the importance of position in saliency comparison, we preserve absolute coordinates of objects in ROI pooling operation and then fuse positional information with semantic features in the first stage. In the feature interaction stage, we apply the attention mechanism to obtain proposals' contextualized representations to predict their relative ranking orders. Extensive experiments have been conducted on the ASR dataset. Without bells and whistles, our proposed method outperforms the former state-of-the-art method significantly. The code will be released publicly available.

Hao Feng, Minghao Chen, Jinming Hu et al.

In recent years, supervised person re-identification (re-ID) models have received increasing studies. However, these models trained on the source domain always suffer dramatic performance drop when tested on an unseen domain. Existing methods are primary to use pseudo labels to alleviate this problem. One of the most successful approaches predicts neighbors of each unlabeled image and then uses them to train the model. Although the predicted neighbors are credible, they always miss some hard positive samples, which may hinder the model from discovering important discriminative information of the unlabeled domain. In this paper, to complement these low recall neighbor pseudo labels, we propose a joint learning framework to learn better feature embeddings via high precision neighbor pseudo labels and high recall group pseudo labels. The group pseudo labels are generated by transitively merging neighbors of different samples into a group to achieve higher recall. However, the merging operation may cause subgroups in the group due to imperfect neighbor predictions. To utilize these group pseudo labels properly, we propose using a similarity-aggregating loss to mitigate the influence of these subgroups by pulling the input sample towards the most similar embeddings. Extensive experiments on three large-scale datasets demonstrate that our method can achieve state-of-the-art performance under the unsupervised domain adaptation re-ID setting.

Hao-Zhe Feng, Kezhi Kong, Minghao Chen et al.

Semi-supervised variational autoencoders (VAEs) have obtained strong results, but have also encountered the challenge that good ELBO values do not always imply accurate inference results. In this paper, we investigate and propose two causes of this problem: (1) The ELBO objective cannot utilize the label information directly. (2) A bottleneck value exists and continuing to optimize ELBO after this value will not improve inference accuracy. On the basis of the experiment results, we propose SHOT-VAE to address these problems without introducing additional prior knowledge. The SHOT-VAE offers two contributions: (1) A new ELBO approximation named smooth-ELBO that integrates the label predictive loss into ELBO. (2) An approximation based on optimal interpolation that breaks the ELBO value bottleneck by reducing the margin between ELBO and the data likelihood. The SHOT-VAE achieves good performance with a 25.30% error rate on CIFAR-100 with 10k labels and reduces the error rate to 6.11% on CIFAR-10 with 4k labels.

Hao-Zhe Feng, Zhaoyang You, Minghao Chen et al.

Conventional unsupervised multi-source domain adaptation (UMDA) methods assume all source domains can be accessed directly. This neglects the privacy-preserving policy, that is, all the data and computations must be kept decentralized. There exists three problems in this scenario: (1) Minimizing the domain distance requires the pairwise calculation of the data from source and target domains, which is not accessible. (2) The communication cost and privacy security limit the application of UMDA methods (e.g., the domain adversarial training). (3) Since users have no authority to check the data quality, the irrelevant or malicious source domains are more likely to appear, which causes negative transfer. In this study, we propose a privacy-preserving UMDA paradigm named Knowledge Distillation based Decentralized Domain Adaptation (KD3A), which performs domain adaptation through the knowledge distillation on models from different source domains. KD3A solves the above problems with three components: (1) A multi-source knowledge distillation method named Knowledge Vote to learn high-quality domain consensus knowledge. (2) A dynamic weighting strategy named Consensus Focus to identify both the malicious and irrelevant domains. (3) A decentralized optimization strategy for domain distance named BatchNorm MMD. The extensive experiments on DomainNet demonstrate that KD3A is robust to the negative transfer and brings a 100x reduction of communication cost compared with other decentralized UMDA methods. Moreover, our KD3A significantly outperforms state-of-the-art UMDA approaches.

Wenxiao Wang, Minghao Chen, Shuai Zhao et al.

Most neural network pruning methods, such as filter-level and layer-level prunings, prune the network model along one dimension (depth, width, or resolution) solely to meet a computational budget. However, such a pruning policy often leads to excessive reduction of that dimension, thus inducing a huge accuracy loss. To alleviate this issue, we argue that pruning should be conducted along three dimensions comprehensively. For this purpose, our pruning framework formulates pruning as an optimization problem. Specifically, it first casts the relationships between a certain model's accuracy and depth/width/resolution into a polynomial regression and then maximizes the polynomial to acquire the optimal values for the three dimensions. Finally, the model is pruned along the three optimal dimensions accordingly. In this framework, since collecting too much data for training the regression is very time-costly, we propose two approaches to lower the cost: 1) specializing the polynomial to ensure an accurate regression even with less training data; 2) employing iterative pruning and fine-tuning to collect the data faster. Extensive experiments show that our proposed algorithm surpasses state-of-the-art pruning algorithms and even neural architecture search-based algorithms.

Wenxiao Wang, Shuai Zhao, Minghao Chen et al.

Neural network pruning is one of the most popular methods of accelerating the inference of deep convolutional neural networks (CNNs). The dominant pruning methods, filter-level pruning methods, evaluate their performance through the reduction ratio of computations and deem that a higher reduction ratio of computations is equivalent to a higher acceleration ratio in terms of inference time. However, we argue that they are not equivalent if parallel computing is considered. Given that filter-level pruning only prunes filters in layers and computations in a layer usually run in parallel, most computations reduced by filter-level pruning usually run in parallel with the un-reduced ones. Thus, the acceleration ratio of filter-level pruning is limited. To get a higher acceleration ratio, it is better to prune redundant layers because computations of different layers cannot run in parallel. In this paper, we propose our Discrimination based Block-level Pruning method (DBP). Specifically, DBP takes a sequence of consecutive layers (e.g., Conv-BN-ReLu) as a block and removes redundant blocks according to the discrimination of their output features. As a result, DBP achieves a considerable acceleration ratio by reducing the depth of CNNs. Extensive experiments show that DBP has surpassed state-of-the-art filter-level pruning methods in both accuracy and acceleration ratio. Our code will be made available soon.

Minghao Chen, Hongyang Xue, Deng Cai

Deep neural networks for semantic segmentation always require a large number of samples with pixel-level labels, which becomes the major difficulty in their real-world applications. To reduce the labeling cost, unsupervised domain adaptation (UDA) approaches are proposed to transfer knowledge from labeled synthesized datasets to unlabeled real-world datasets. Recently, some semi-supervised learning methods have been applied to UDA and achieved state-of-the-art performance. One of the most popular approaches in semi-supervised learning is the entropy minimization method. However, when applying the entropy minimization to UDA for semantic segmentation, the gradient of the entropy is biased towards samples that are easy to transfer. To balance the gradient of well-classified target samples, we propose the maximum squares loss. Our maximum squares loss prevents the training process being dominated by easy-to-transfer samples in the target domain. Besides, we introduce the image-wise weighting ratio to alleviate the class imbalance in the unlabeled target domain. Both synthetic-to-real and cross-city adaptation experiments demonstrate the effectiveness of our proposed approach. The code is released at https://github. com/ZJULearning/MaxSquareLoss.

Qing Lyu, Minghao Chen, Xiang Chen

Cloud segmentation plays a crucial role in image analysis for climate modeling. Manually labeling the training data for cloud segmentation is time-consuming and error-prone. We explore to train segmentation networks with synthetic data due to the natural acquisition of pixel-level labels. Nevertheless, the domain gap between synthetic and real images significantly degrades the performance of the trained model. We propose a color space adaptation method to bridge the gap, by training a color-sensitive generator and discriminator to adapt synthetic data to real images in color space. Instead of transforming images by general convolutional kernels, we adopt a set of closed-form operations to make color-space adjustments while preserving the labels. We also construct a synthetic-to-real cirrus cloud dataset SynCloud and demonstrate the adaptation efficacy on the semantic segmentation task of cirrus clouds. With our adapted synthetic data for training the semantic segmentation, we achieve an improvement of 6:59% when applied to real images, superior to alternative methods.