Ye Huang

Ye Huang, Di Kang, Liang Chen et al.

Recent segmentation methods, such as OCR and CPNet, utilizing "class level" information in addition to pixel features, have achieved notable success for boosting the accuracy of existing network modules. However, the extracted class-level information was simply concatenated to pixel features, without explicitly being exploited for better pixel representation learning. Moreover, these approaches learn soft class centers based on coarse mask prediction, which is prone to error accumulation. In this paper, aiming to use class level information more effectively, we propose a universal Class-Aware Regularization (CAR) approach to optimize the intra-class variance and inter-class distance during feature learning, motivated by the fact that humans can recognize an object by itself no matter which other objects it appears with. Three novel loss functions are proposed. The first loss function encourages more compact class representations within each class, the second directly maximizes the distance between different class centers, and the third further pushes the distance between inter-class centers and pixels. Furthermore, the class center in our approach is directly generated from ground truth instead of from the error-prone coarse prediction. Our method can be easily applied to most existing segmentation models during training, including OCR and CPNet, and can largely improve their accuracy at no additional inference overhead. Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2.23% mIOU with superior generalization ability. The complete code is available at https://github.com/edwardyehuang/CAR.

Ye Huang, Di Kang, Shenghua Gao et al.

Existing pyramid-based upsamplers (e.g. SemanticFPN), although efficient, usually produce less accurate results compared to dilation-based models when using the same backbone. This is partially caused by the contaminated high-level features since they are fused and fine-tuned with noisy low-level features on limited data. To address this issue, we propose to use powerful pre-trained high-level features as guidance (HFG) so that the upsampler can produce robust results. Specifically, \emph{only} the high-level features from the backbone are used to train the class tokens, which are then reused by the upsampler for classification, guiding the upsampler features to more discriminative backbone features. One crucial design of the HFG is to protect the high-level features from being contaminated by using proper stop-gradient operations so that the backbone does not update according to the noisy gradient from the upsampler. To push the upper limit of HFG, we introduce a context augmentation encoder (CAE) that can efficiently and effectively operate on the low-resolution high-level feature, resulting in improved representation and thus better guidance. We named our complete solution as the High-Level Features Guided Decoder (HFGD). We evaluate the proposed HFGD on three benchmarks: Pascal Context, COCOStuff164k, and Cityscapes. HFGD achieves state-of-the-art results among methods that do not use extra training data, demonstrating its effectiveness and generalization ability.

Ye Huang, Di Kang, Liang Chen et al.

Semantic segmentation has recently achieved notable advances by exploiting "class-level" contextual information during learning. However, these approaches simply concatenate class-level information to pixel features to boost the pixel representation learning, which cannot fully utilize intra-class and inter-class contextual information. Moreover, these approaches learn soft class centers based on coarse mask prediction, which is prone to error accumulation. To better exploit class level information, we propose a universal Class-Aware Regularization (CAR) approach to optimize the intra-class variance and inter-class distance during feature learning, motivated by the fact that humans can recognize an object by itself no matter which other objects it appears with. Moreover, we design a dedicated decoder for CAR (CARD), which consists of a novel spatial token mixer and an upsampling module, to maximize its gain for existing baselines while being highly efficient in terms of computational cost. Specifically, CAR consists of three novel loss functions. The first loss function encourages more compact class representations within each class, the second directly maximizes the distance between different class centers, and the third further pushes the distance between inter-class centers and pixels. Furthermore, the class center in our approach is directly generated from ground truth instead of from the error-prone coarse prediction. CAR can be directly applied to most existing segmentation models during training, and can largely improve their accuracy at no additional inference overhead. Extensive experiments and ablation studies conducted on multiple benchmark datasets demonstrate that the proposed CAR can boost the accuracy of all baseline models by up to 2.23% mIOU with superior generalization ability. CARD outperforms SOTA approaches on multiple benchmarks with a highly efficient architecture.

Yanqi Ge, Qiang Nie, Ye Huang et al.

One of the ultimate goals of representation learning is to achieve compactness within a class and well-separability between classes. Many outstanding metric-based and prototype-based methods following the Expectation-Maximization paradigm, have been proposed for this objective. However, they inevitably introduce biases into the learning process, particularly with long-tail distributed training data. In this paper, we reveal that the class prototype is not necessarily to be derived from training features and propose a novel perspective to use pre-defined class anchors serving as feature centroid to unidirectionally guide feature learning. However, the pre-defined anchors may have a large semantic distance from the pixel features, which prevents them from being directly applied. To address this issue and generate feature centroid independent from feature learning, a simple yet effective Semantic Anchor Regularization (SAR) is proposed. SAR ensures the interclass separability of semantic anchors in the semantic space by employing a classifier-aware auxiliary cross-entropy loss during training via disentanglement learning. By pulling the learned features to these semantic anchors, several advantages can be attained: 1) the intra-class compactness and naturally inter-class separability, 2) induced bias or errors from feature learning can be avoided, and 3) robustness to the long-tailed problem. The proposed SAR can be used in a plug-and-play manner in the existing models. Extensive experiments demonstrate that the SAR performs better than previous sophisticated prototype-based methods. The implementation is available at https://github.com/geyanqi/SAR.

Kewei Zhang, Ye Huang, Yufan Deng et al.

While the Transformer architecture dominates many fields, its quadratic self-attention complexity hinders its use in large-scale applications. Linear attention offers an efficient alternative, but its direct application often degrades performance, with existing fixes typically re-introducing computational overhead through extra modules (e.g., depthwise separable convolution) that defeat the original purpose. In this work, we identify a key failure mode in these methods: global context collapse, where the model loses representational diversity. To address this, we propose Multi-Head Linear Attention (MHLA), which preserves this diversity by computing attention within divided heads along the token dimension. We prove that MHLA maintains linear complexity while recovering much of the expressive power of softmax attention, and verify its effectiveness across multiple domains, achieving a 3.6\% improvement on ImageNet classification, a 6.3\% gain on NLP, a 12.6\% improvement on image generation, and a 41\% enhancement on video generation under the same time complexity.

Linlong Fan, Ye Huang, Yanqi Ge et al.

Existing view-based methods excel at recognizing 3D objects from predefined viewpoints, but their exploration of recognition under arbitrary views is limited. This is a challenging and realistic setting because each object has different viewpoint positions and quantities, and their poses are not aligned. However, most view-based methods, which aggregate multiple view features to obtain a global feature representation, hard to address 3D object recognition under arbitrary views. Due to the unaligned inputs from arbitrary views, it is challenging to robustly aggregate features, leading to performance degradation. In this paper, we introduce a novel Part-aware Network (PANet), which is a part-based representation, to address these issues. This part-based representation aims to localize and understand different parts of 3D objects, such as airplane wings and tails. It has properties such as viewpoint invariance and rotation robustness, which give it an advantage in addressing the 3D object recognition problem under arbitrary views. Our results on benchmark datasets clearly demonstrate that our proposed method outperforms existing view-based aggregation baselines for the task of 3D object recognition under arbitrary views, even surpassing most fixed viewpoint methods.

Yu Xiong, Zhipeng Hu, Ye Huang et al.

Reinforcement Learning (RL) has demonstrated substantial potential across diverse fields, yet understanding its decision-making process, especially in real-world scenarios where rationality and safety are paramount, is an ongoing challenge. This paper delves in to Explainable RL (XRL), a subfield of Explainable AI (XAI) aimed at unravelling the complexities of RL models. Our focus rests on state-explaining techniques, a crucial subset within XRL methods, as they reveal the underlying factors influencing an agent's actions at any given time. Despite their significant role, the lack of a unified evaluation framework hinders assessment of their accuracy and effectiveness. To address this, we introduce XRL-Bench, a unified standardized benchmark tailored for the evaluation and comparison of XRL methods, encompassing three main modules: standard RL environments, explainers based on state importance, and standard evaluators. XRL-Bench supports both tabular and image data for state explanation. We also propose TabularSHAP, an innovative and competitive XRL method. We demonstrate the practical utility of TabularSHAP in real-world online gaming services and offer an open-source benchmark platform for the straightforward implementation and evaluation of XRL methods. Our contributions facilitate the continued progression of XRL technology.

Zhilin Liu, Ye Huang, Ting Xie et al.

Recent advances in Large Language Model (LLM)-based agents have shown remarkable progress in code generation. However, current agent methods mainly rely on text-output-based feedback (e.g. command-line outputs) for multi-round debugging and struggle in graphical user interface (GUI) that involve visual information. This is mainly due to two limitations: 1) GUI programs are event-driven, yet existing methods cannot simulate user interactions to trigger GUI element logic 2) GUI programs possess visual attributes, making it difficult for text-based approaches to assess whether the rendered interface meets user needs. To systematically address these challenges, we first introduce InteractGUI Bench, a novel benchmark comprising 984 commonly used real-world desktop GUI application tasks designed for fine-grained evaluation of both interaction logic and visual structure. Furthermore, we propose VF-Coder, a vision-feedback-based multi-agent system for debugging GUI code. By perceiving visual information and directly interacting with program interfaces, VF-Coder can identify potential logic and layout issues in a human-like manner. On InteractGUI Bench, our VF-Coder approach increases the success rate of Gemini-3-Flash from 21.68% to 28.29% and raises the visual score from 0.4284 to 0.5584, indicating the effectiveness of visual feedback in GUI debugging.

Ruizhi Zhang, Ye Huang, Yuangang Pan et al.

While Vision-Language Models (VLMs) have achieved remarkable progress in static visual understanding, their deployment in complex 3D embodied environments remains severely limited. Existing benchmarks suffer from four critical deficiencies: (1) passive perception tasks circumvent interactive dynamics; (2) simplified 2D environments fail to assess depth perception; (3) privileged state leakage bypasses genuine visual processing; and (4) human evaluation is prohibitively expensive and unscalable. We introduce PokeGym, a visually-driven long-horizon benchmark instantiated within Pokemon Legends: Z-A, a visually complex 3D open-world Role-Playing Game. PokeGym enforces strict code-level isolation: agents operate solely on raw RGB observations while an independent evaluator verifies success via memory scanning, ensuring pure vision-based decision-making and automated, scalable assessment. The benchmark comprises 30 tasks (30-220 steps) spanning navigation, interaction, and mixed scenarios, with three instruction granularities (Visual-Guided, Step-Guided, Goal-Only) to systematically deconstruct visual grounding, semantic reasoning, and autonomous exploration capabilities. Our evaluation reveals a key limitation of current VLMs: physical deadlock recovery, rather than high-level planning, constitutes the primary bottleneck, with deadlocks showing a strong negative correlation with task success. Furthermore, we uncover a metacognitive divergence: weaker models predominantly suffer from Unaware Deadlocks (oblivious to entrapment), whereas advanced models exhibit Aware Deadlocks (recognizing entrapment yet failing to recover). These findings highlight the need to integrate explicit spatial intuition into VLM architectures. The code and benchmark will be available on GitHub.

Zixi Liang, Guowei Xu, Haifeng Wu et al.

Learning-based methods have become increasingly popular in 3D indoor scene synthesis (ISS), showing superior performance over traditional optimization-based approaches. These learning-based methods typically model distributions on simple yet explicit scene representations using generative models. However, due to the oversimplified explicit representations that overlook detailed information and the lack of guidance from multimodal relationships within the scene, most learning-based methods struggle to generate indoor scenes with realistic object arrangements and styles. In this paper, we introduce a new method, Scene Implicit Neural Field (S-INF), for indoor scene synthesis, aiming to learn meaningful representations of multimodal relationships, to enhance the realism of indoor scene synthesis. S-INF assumes that the scene layout is often related to the object-detailed information. It disentangles the multimodal relationships into scene layout relationships and detailed object relationships, fusing them later through implicit neural fields (INFs). By learning specialized scene layout relationships and projecting them into S-INF, we achieve a realistic generation of scene layout. Additionally, S-INF captures dense and detailed object relationships through differentiable rendering, ensuring stylistic consistency across objects. Through extensive experiments on the benchmark 3D-FRONT dataset, we demonstrate that our method consistently achieves state-of-the-art performance under different types of ISS.

Hao Liu, Ye Huang, Chenghuan Huang et al.

Video Diffusion Transformer (DiT) models are a dominant approach for high-quality video generation but suffer from high inference cost due to iterative denoising. Existing caching approaches primarily exploit similarity within the diffusion process of a single request to skip redundant denoising steps. In this paper, we introduce Chorus, a caching approach that leverages similarity across requests to accelerate video diffusion model serving. Chorus achieves up to 45\% speedup on industrial 4-step distilled models, where prior intra-request caching approaches are ineffective. Particularly, Chorus employs a three-stage caching strategy along the denoising process. Stage 1 performs full reuse of latent features from similar requests. Stage 2 exploits inter-request caching in specific latent regions during intermediate denoising steps. This stage is combined with Token-Guided Attention Amplification to improve semantic alignment between the generated video and the conditional prompts, thereby extending the applicability of full reuse to later denoising steps.

Xikai Tang, Ye Huang, Guangqiang Yin et al.

We present VPNeXt, a new and simple model for the Plain Vision Transformer (ViT). Unlike the many related studies that share the same homogeneous paradigms, VPNeXt offers a fresh perspective on dense representation based on ViT. In more detail, the proposed VPNeXt addressed two concerns about the existing paradigm: (1) Is it necessary to use a complex Transformer Mask Decoder architecture to obtain good representations? (2) Does the Plain ViT really need to depend on the mock pyramid feature for upsampling? For (1), we investigated the potential underlying reasons that contributed to the effectiveness of the Transformer Decoder and introduced the Visual Context Replay (VCR) to achieve similar effects efficiently. For (2), we introduced the ViTUp module. This module fully utilizes the previously overlooked ViT real pyramid feature to achieve better upsampling results compared to the earlier mock pyramid feature. This represents the first instance of such functionality in the field of semantic segmentation for Plain ViT. We performed ablation studies on related modules to verify their effectiveness gradually. We conducted relevant comparative experiments and visualizations to show that VPNeXt achieved state-of-the-art performance with a simple and effective design. Moreover, the proposed VPNeXt significantly exceeded the long-established mIoU wall/barrier of the VOC2012 dataset, setting a new state-of-the-art by a large margin, which also stands as the largest improvement since 2015.

Yanqi Ge, Jiaqi Liu, Qingnan Fan et al.

In this work, we target the task of text-driven style transfer in the context of text-to-image (T2I) diffusion models. The main challenge is consistent structure preservation while enabling effective style transfer effects. The past approaches in this field directly concatenate the content and style prompts for a prompt-level style injection, leading to unavoidable structure distortions. In this work, we propose a novel solution to the text-driven style transfer task, namely, Adaptive Style Incorporation~(ASI), to achieve fine-grained feature-level style incorporation. It consists of the Siamese Cross-Attention~(SiCA) to decouple the single-track cross-attention to a dual-track structure to obtain separate content and style features, and the Adaptive Content-Style Blending (AdaBlending) module to couple the content and style information from a structure-consistent manner. Experimentally, our method exhibits much better performance in both structure preservation and stylized effects.

Jiarui Chen, Yikeng Chen, Yingshuang Zou et al.

3D Gaussian Splatting (3DGS) has emerged as a dominant novel-view synthesis technique, but its high memory consumption severely limits its applicability on edge devices. A growing number of 3DGS compression methods have been proposed to make 3DGS more efficient, yet most only focus on storage compression and fail to address the critical bottleneck of rendering memory. To address this problem, we introduce MEGS$^{2}$, a novel memory-efficient framework that tackles this challenge by jointly optimizing two key factors: the total primitive number and the parameters per primitive, achieving unprecedented memory compression. Specifically, we replace the memory-intensive spherical harmonics with lightweight, arbitrarily oriented spherical Gaussian lobes as our color representations. More importantly, we propose a unified soft pruning framework that models primitive-number and lobe-number pruning as a single constrained optimization problem. Experiments show that MEGS$^{2}$ achieves a 50% static VRAM reduction and a 40% rendering VRAM reduction compared to existing methods, while maintaining comparable rendering quality. Project page: https://megs-2.github.io/

Xie Ting, Ye Huang, Zhilin Liu et al.

In real-world scenarios, pixel-level labeling is not always available. Sometimes, we need a semantic segmentation network, and even a visual encoder can have a high compatibility, and can be trained using various types of feedback beyond traditional labels, such as feedback that indicates the quality of the parsing results. To tackle this issue, we proposed RSS (Reward in Semantic Segmentation), the first practical application of reward-based reinforcement learning on pure semantic segmentation offered in two granular levels (pixel-level and image-level). RSS incorporates various novel technologies, such as progressive scale rewards (PSR) and pair-wise spatial difference (PSD), to ensure that the reward facilitates the convergence of the semantic segmentation network, especially under image-level rewards. Experiments and visualizations on benchmark datasets demonstrate that the proposed RSS can successfully ensure the convergence of the semantic segmentation network on two levels of rewards. Additionally, the RSS, which utilizes an image-level reward, outperforms existing weakly supervised methods that also rely solely on image-level signals during training.

Yanqi Ge, Ye Huang, Wen Li et al.

We introduced SSR, which utilizes SAM (segment-anything) as a strong regularizer during training, to greatly enhance the robustness of the image encoder for handling various domains. Specifically, given the fact that SAM is pre-trained with a large number of images over the internet, which cover a diverse variety of domains, the feature encoding extracted by the SAM is obviously less dependent on specific domains when compared to the traditional ImageNet pre-trained image encoder. Meanwhile, the ImageNet pre-trained image encoder is still a mature choice of backbone for the semantic segmentation task, especially when the SAM is category-irrelevant. As a result, our SSR provides a simple yet highly effective design. It uses the ImageNet pre-trained image encoder as the backbone, and the intermediate feature of each stage (ie there are 4 stages in MiT-B5) is regularized by SAM during training. After extensive experimentation on GTA5$\rightarrow$Cityscapes, our SSR significantly improved performance over the baseline without introducing any extra inference overhead.

Ye Huang, Di Kang, Wenjing Jia et al.

Spatial and channel attentions, modelling the semantic interdependencies in spatial and channel dimensions respectively, have recently been widely used for semantic segmentation. However, computing spatial and channel attentions separately sometimes causes errors, especially for those difficult cases. In this paper, we propose Channelized Axial Attention (CAA) to seamlessly integrate channel attention and spatial attention into a single operation with negligible computation overhead. Specifically, we break down the dot-product operation of the spatial attention into two parts and insert channel relation in between, allowing for independently optimized channel attention on each spatial location. We further develop grouped vectorization, which allows our model to run with very little memory consumption without slowing down the running speed. Comparative experiments conducted on multiple benchmark datasets, including Cityscapes, PASCAL Context, and COCO-Stuff, demonstrate that our CAA outperforms many state-of-the-art segmentation models (including dual attention) on all tested datasets.

Ye Huang, Qingqing Wang, Wenjing Jia et al.

The state-of-the-art semantic segmentation solutions usually leverage different receptive fields via multiple parallel branches to handle objects with different sizes. However, employing separate kernels for individual branches degrades the generalization and representation abilities of the network, and the number of parameters increases linearly in the number of branches. To tackle this problem, we propose a novel network structure namely Kernel-Sharing Atrous Convolution (KSAC), where branches of different receptive fields share the same kernel, i.e., let a single kernel see the input feature maps more than once with different receptive fields, to facilitate communication among branches and perform feature augmentation inside the network. Experiments conducted on the benchmark PASCAL VOC 2012 dataset show that the proposed sharing strategy can not only boost a network s generalization and representation abilities but also reduce the model complexity significantly. Specifically, on the validation set, whe compared with DeepLabV3+ equipped with MobileNetv2 backbone, 33% of parameters are reduced together with an mIOU improvement of 0.6%. When Xception is used as the backbone, the mIOU is elevated from 83.34% to 85.96% with about 10M parameters saved. In addition, different from the widely used ASPP structure, our proposed KSAC is able to further improve the mIOU by taking benefit of wider context with larger atrous rates. Finally, our KSAC achieves mIOUs of 88.1% and 45.47% on the PASCAL VOC 2012 test set and ADE20K dataset, respectively. Our full code will be released on the Github.

Qingqing Wang, Wenjing Jia, Xiangjian He et al.

Scene text recognition has recently been widely treated as a sequence-to-sequence prediction problem, where traditional fully-connected-LSTM (FC-LSTM) has played a critical role. Due to the limitation of FC-LSTM, existing methods have to convert 2-D feature maps into 1-D sequential feature vectors, resulting in severe damages of the valuable spatial and structural information of text images. In this paper, we argue that scene text recognition is essentially a spatiotemporal prediction problem for its 2-D image inputs, and propose a convolution LSTM (ConvLSTM)-based scene text recognizer, namely, FACLSTM, i.e., Focused Attention ConvLSTM, where the spatial correlation of pixels is fully leveraged when performing sequential prediction with LSTM. Particularly, the attention mechanism is properly incorporated into an efficient ConvLSTM structure via the convolutional operations and additional character center masks are generated to help focus attention on right feature areas. The experimental results on benchmark datasets IIIT5K, SVT and CUTE demonstrate that our proposed FACLSTM performs competitively on the regular, low-resolution and noisy text images, and outperforms the state-of-the-art approaches on the curved text with large margins.