4 papers
Mitigating the ID-OOD Tradeoff in Open-Set Test-Time Adaptation
Wenjie Zhao, Jia Li, Xin Dong +3
Open-set test-time adaptation (OSTTA) addresses the challenge of adapting models to new environments where out-of-distribution (OOD) samples coexist with in-distribution (ID) sampl…
Multimodal Reference Visual Grounding
Yangxiao Lu, Ruosen Li, Liqiang Jing +5
Visual grounding focuses on detecting objects from images based on language expressions. Recent Large Vision-Language Models (LVLMs) have significantly advanced visual grounding pe…
Continual Distillation Learning for Rehearsal-Free Class-Incremental Learning via Decoupled Prompting
Qifan Zhang, Yunhui Guo, Yu Xiang
Prompt-based continual learning has shown strong performance in rehearsal-free class-incremental learning by adapting learnable prompts while freezing a pre-trained Vision Transfor…
Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation
Yangxiao Lu, Jishnu Jaykumar P, Yunhui Guo +2
Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet ef…