2 papers
cs.CV2026
G2D: Generative-to-Discriminative Collaborative Inference for Zero-Shot Image Classification
Zehua Hao, Fang Liu, Qinliang Wang +3
Zero-shot classification needs efficient label retrieval and fine-grained visual reasoning, yet discriminative and generative vision-language models fail in complementary ways.When…
cs.CV2025
Logits DeConfusion with CLIP for Few-Shot Learning
Shuo Li, Fang Liu, Zehua Hao +5
With its powerful visual-language alignment capability, CLIP performs well in zero-shot and few-shot learning tasks. However, we found in experiments that CLIP's logits suffer from…