5 citations · 5 across the 11 of their papers we have counts for
12 papers · 1 filter
Breaking the Synthetic-Real Domain Shortcut for Training-Free Generative Replay-based Class Incremental Learning
Tao Zhang, Qixuan Fan, Yiyuan Liang +7
Class-incremental learning (CIL) requires models to continuously acquire new knowledge while avoiding catastrophic forgetting. While exemplar replay is effective, it raises concern…
Vision-Language Attribute Disentanglement and Reinforcement for Lifelong Person Re-Identification
Kunlun Xu, Haotong Cheng, Jiangmeng Li +2
Lifelong person re-identification (LReID) aims to learn from varying domains to obtain a unified person retrieval model. Existing LReID approaches typically focus on learning from…
State Space Prompting via Gathering and Spreading Spatio-Temporal Information for Video Understanding
Jiahuan Zhou, Kai Zhu, Zhenyu Cui +3
Recently, pre-trained state space models have shown great potential for video classification, which sequentially compresses visual tokens in videos with linear complexity, thereby…
Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation
Jiahuan Zhou, Chao Zhu, Zhenyu Cui +3
Continual Test-Time Adaptation (CTTA) aims to quickly fine-tune the model during the test phase so that it can adapt to multiple unknown downstream domain distributions without pre…
Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identification
Kunlun Xu, Fan Zhuo, Jiangmeng Li +2
Current lifelong person re-identification (LReID) methods predominantly rely on fully labeled data streams. However, in real-world scenarios where annotation resources are limited,…
Vision Graph Prompting via Semantic Low-Rank Decomposition
Zixiang Ai, Zichen Liu, Jiahuan Zhou
Vision GNN (ViG) demonstrates superior performance by representing images as graph structures, providing a more natural way to capture irregular semantic patterns beyond traditiona…
Componential Prompt-Knowledge Alignment for Domain Incremental Learning
Kunlun Xu, Xu Zou, Gang Hua +1
Domain Incremental Learning (DIL) aims to learn from non-stationary data streams across domains while retaining and utilizing past knowledge. Although prompt-based methods effectiv…
Token Coordinated Prompt Attention is Needed for Visual Prompting
Zichen Liu, Xu Zou, Gang Hua +1
Visual prompting techniques are widely used to efficiently fine-tune pretrained Vision Transformers (ViT) by learning a small set of shared prompts for all tokens. However, existin…
GAPrompt: Geometry-Aware Point Cloud Prompt for 3D Vision Model
Zixiang Ai, Zichen Liu, Yuanhang Lei +3
Pre-trained 3D vision models have gained significant attention for their promising performance on point cloud data. However, fully fine-tuning these models for downstream tasks is…
Incremental Object Keypoint Learning
Mingfu Liang, Jiahuan Zhou, Xu Zou +1
Existing progress in object keypoint estimation primarily benefits from the conventional supervised learning paradigm based on numerous data labeled with pre-defined keypoints. How…
DriveEditor: A Unified 3D Information-Guided Framework for Controllable Object Editing in Driving Scenes
Yiyuan Liang, Zhiying Yan, Liqun Chen +4
Vision-centric autonomous driving systems require diverse data for robust training and evaluation, which can be augmented by manipulating object positions and appearances within ex…
Make Lossy Compression Meaningful for Low-Light Images
Shilv Cai, Liqun Chen, Sheng Zhong +3
Low-light images frequently occur due to unavoidable environmental influences or technical limitations, such as insufficient lighting or limited exposure time. To achieve better vi…