Sep 2026
HyperCLIP++: Fine-Tuning CLIP for Open-Vocabulary Semantic Segmentation in Hyperbolic Space.
CLIP, a foundational vision-language model, has emerged as a powerful tool for open-vocabulary semantic segmentation. While freezing CLIP's text encoder is known to preserve its generalization capability, recent studies show that fine-tuning both CLIP's text and image encoders jointly significantly enhances segmentatio...
Ze-Lin Peng, Zheng-Qin Xu, Chang-Song Wen et al.
· IEEE Transactions on Pattern... · 0 citations