7 papers
Towards Joint Quantization and Token Pruning of Vision-Language Models
Xinqing Li, Xin He, Xindong Zhang +3
Deploying Vision-Language Models (VLMs) under aggressive low-bit inference remains challenging because inference cost is dominated by the long visual-token prefix during prefill an…
The Second Challenge on Cross-Domain Few-Shot Object Detection at NTIRE 2026: Methods and Results
Xingyu Qiu, Yuqian Fu, Jiawei Geng +70
Cross-domain few-shot object detection (CD-FSOD) remains a challenging problem for existing object detectors and few-shot learning approaches, particularly when generalizing across…
Certainty Is Redundant: Token Sparsification for Efficient Camouflaged Object Detection with Vision Foundation Models
Yuhan Gao, Shuhao Kang, Xin He +3
Camouflaged object detection (COD) aims to segment objects that closely resemble their surrounding environments. Vision foundation models (VFMs) provide strong transferable represe…
Amped: Adaptive Multi-stage Non-edge Pruning for Edge Detection
Yuhan Gao, Xinqing Li, Xin He +4
Edge detection is a fundamental image analysis task that underpins numerous high-level vision applications. Recent advances in Transformer architectures have significantly improved…
Make It Up: Fake Images, Real Gains in Generalized Few-shot Semantic Segmentation
Guohuan Xie, Xin He, Dingying Fan +3
Generalized few-shot semantic segmentation (GFSS) is fundamentally limited by the coverage of novel-class appearances under scarce annotations. While diffusion models can synthesiz…
A Comprehensive Survey on Video Scene Parsing:Advances, Challenges, and Prospects
Guohuan Xie, Syed Ariff Syed Hesham, Wenya Guo +4
Video Scene Parsing (VSP) studies dense video understanding, where every pixel in each frame must be segmented, each region must be named, and each object identity must remain cohe…
Multimodality Helps Few-shot 3D Point Cloud Semantic Segmentation
Zhaochong An, Guolei Sun, Yun Liu +5
Few-shot 3D point cloud segmentation (FS-PCS) aims at generalizing models to segment novel categories with minimal annotated support samples. While existing FS-PCS methods have sho…