Publications (23)
Classification Calibration for Long-tail Instance Segmentation
Tao Wang, Yu Li, Bingyi Kang +5
Remarkable progress has been made in object instance detection and segmentation in recent years. However, existing state-of-the-art methods are mostly evaluated with fairly balance…
CGNet: A Light-weight Context Guided Network for Semantic Segmentation
Tianyi Wu, Sheng Tang, Rui Zhang +1
The demand of applying semantic segmentation model on mobile devices has been increasing rapidly. Current state-of-the-art networks have enormous amount of parameters hence unsuita…
Overcoming Classifier Imbalance for Long-tail Object Detection with Balanced Group Softmax
Yu Li, Tao Wang, Bingyi Kang +4
Solving long-tail large vocabulary object detection with deep learning based models is a challenging and demanding task, which is however under-explored.In this work, we provide th…
Beyond Semantic Features: Pixel-level Mapping for Generalized AI-Generated Image Detection
Chenming Zhou, Jiaan Wang, Yu Li +3
The rapid evolution of generative technologies necessitates reliable methods for detecting AI-generated images. A critical limitation of current detectors is their failure to gener…
GeV γ-ray emission in the low-mass star-forming region AFGL 490
Li-Nuo Yang, Sheng Tang, Pak-Hin Thomas Tam
We report the discovery of an extended GeV γ-ray source, 4FGL J0330.7+5845e, associated with the star-forming region AFGL 490 using 17 years of Fermi-LAT data. The emission is spa…
Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
Ming Chen, Sheng Tang, Rong-Xi Tan +4
Decoding-based regression, which reformulates regression as a sequence generation task, has emerged as a promising paradigm of applying large language models for numerical predicti…
Quality-Diversity Red-Teaming: Automated Generation of High-Quality and Diverse Attackers for Large Language Models
Ren-Jian Wang, Ke Xue, Zeyu Qin +7
Ensuring the safety and robustness of large language models (LLMs) is a fundamental challenge and a critical prerequisite for the responsible deployment of artificial intelligence.…
TryOnCrafter: Unleashing Camera Trajectories for Realistic Video Virtual Try-on via a Renderable 4D Try-on Proxy
Hao Sun, Hao Yan, Mengting Chen +7
While Video Virtual Try-on (VVT) has achieved remarkable progress in synthesizing realistic garment overlays on dynamic subjects, existing paradigms remains fundamentally constrain…
Learning Monocular Depth from Events via Egomotion Compensation
Haitao Meng, Chonghao Zhong, Sheng Tang +6
Event cameras are neuromorphically inspired sensors that sparsely and asynchronously report brightness changes. Their unique characteristics of high temporal resolution, high dynam…
The Devil is in Classification: A Simple Framework for Long-tail Object Detection and Instance Segmentation
Tao Wang, Yu Li, Bingyi Kang +5
Most existing object instance detection and segmentation models only work well on fairly balanced benchmarks where per-category training sample numbers are comparable, such as COCO…
HDIdx: High-Dimensional Indexing for Efficient Approximate Nearest Neighbor Search
Ji Wan, Sheng Tang, Yongdong Zhang +3
Fast Nearest Neighbor (NN) search is a fundamental challenge in large-scale data processing and analytics, particularly for analyzing multimedia contents which are often of high di…
Attend to Not Attended: Structure-then-Detail Token Merging for Post-training DiT Acceleration
Haipeng Fang, Sheng Tang, Juan Cao +3
Diffusion transformers have shown exceptional performance in visual generation but incur high computational costs. Token reduction techniques that compress models by sharing the de…
Visual Relation Grounding in Videos
Junbin Xiao, Xindi Shang, Xun Yang +2
In this paper, we explore a novel task named visual Relation Grounding in Videos (vRGV). The task aims at spatio-temporally localizing the given relations in the form of subject-pr…
DragEntity: Trajectory Guided Video Generation using Entity and Positional Relationships
Zhang Wan, Sheng Tang, Jiawei Wei +2
In recent years, diffusion models have achieved tremendous success in the field of video generation, with controllable video generation receiving significant attention. However, ex…
Fleet: Few Shots Lead Effective AI-generated Image Detection
Jiaan Wang, Sirui Liu, Yu Li +3
AI-generated image (AIGI) detection is undergoing a critical transition from laboratory benchmarks to open-world adversarial defense. The prevalent paradigm focuses on finding stat…
Topology-preserving Adversarial Training for Alleviating Natural Accuracy Degradation
Xiaoyue Mi, Fan Tang, Yepeng Weng +5
Despite the effectiveness in improving the robustness of neural networks, adversarial training has suffered from the natural accuracy degradation problem, i.e., accuracy on natural…
Tree-structured Kronecker Convolutional Network for Semantic Segmentation
Tianyi Wu, Sheng Tang, Rui Zhang +2
Most existing semantic segmentation methods employ atrous convolution to enlarge the receptive field of filters, but neglect partial information. To tackle this issue, we firstly p…
Learning to Disentangle GAN Fingerprint for Fake Image Attribution
Tianyun Yang, Juan Cao, Qiang Sheng +4
Rapid pace of generative models has brought about new threats to visual forensics such as malicious personation and digital copyright infringement, which promotes works on fake ima…
Dance Your Latents: Consistent Dance Generation through Spatial-temporal Subspace Attention Guided by Motion Flow
Haipeng Fang, Zhihao Sun, Ziyao Huang +3
The advancement of generative AI has extended to the realm of Human Dance Generation, demonstrating superior generative capacities. However, current methods still exhibit deficienc…
Asymmetric GAN for Unpaired Image-to-image Translation
Yu Li, Sheng Tang, Rui Zhang +3
Unpaired image-to-image translation problem aims to model the mapping from one domain to another with unpaired training data. Current works like the well-acknowledged Cycle GAN pro…
Style Separation and Synthesis via Generative Adversarial Networks
Rui Zhang, Sheng Tang, Yu Li +4
Style synthesis attracts great interests recently, while few works focus on its dual problem "style separation". In this paper, we propose the Style Separation and Synthesis Genera…
Progressive Open Space Expansion for Open-Set Model Attribution
Tianyun Yang, Danding Wang, Fan Tang +3
Despite the remarkable progress in generative technology, the Janus-faced issues of intellectual property protection and malicious content supervision have arisen. Efforts have bee…
Consensus Feature Network for Scene Parsing
Tianyi Wu, Sheng Tang, Rui Zhang +2
Scene parsing is challenging as it aims to assign one of the semantic categories to each pixel in scene images. Thus, pixel-level features are desired for scene parsing. However, c…