2 papers
cs.CV2025
Grounding-Aware Token Pruning: Recovering from Drastic Performance Drops in Visual Grounding Caused by Pruning
Tzu-Chun Chien, Chieh-Kai Lin, Shiang-Feng Tsai +3
Recent Multimodal Large Language Models (MLLMs) have demonstrated strong performance in visual grounding, establishing themselves as a general interface for various vision-language…
cs.CV2025
Foreground Focus: Enhancing Coherence and Fidelity in Camouflaged Image Generation
Pei-Chi Chen, Yi Yao, Chan-Feng Hsu +4
Camouflaged image generation is emerging as a solution to data scarcity in camouflaged vision perception, offering a cost-effective alternative to data collection and labeling. Rec…