AI RESEARCH
Direct Segmentation without Logits Optimization for Training-Free Open-Vocabulary Semantic Segmentation
arXiv CS.CV
•
ArXi:2604.07723v1 Announce Type: new Open-vocabulary semantic segmentation (OVSS) aims to segment arbitrary category regions in images using open-vocabulary prompts, necessitating that existing methods possess pixel-level vision-language alignment capability. Typically, this capability involves computing the cosine similarity, \ie, logits, between visual and linguistic features, and minimizing the distribution discrepancy between the logits and the ground truth (GT) to generate optimal logits that are subsequently used to construct segmentation maps, yet it depends on time-consuming iterative.