Mar 18, 2024 · To further prevent potential overfitting in the vision-language aligning process, we propose the affinity and divergence principles to reshape ...

Mar 18, 2024 · We propose the Vision-Language Alignment Learning under Affinity and Divergence Principles (VLAD) to adapt VL-PTMs to robust few-shot OOD generalization with ...

Official implementation of Vision-Language Alignment Learning Under Affinity and Divergence Principles for Few-Shot Out-of-Distribution Generalization.

Mar 18, 2024 · Besides, we introduce affinity and divergence principles to further mitigate overfitting during the vision-language aligning process by ...

The official implementation of Vision-Language Alignment Learning under Affinity and Divergence Principles for Few-Shot Out-of-Distribution Generalization (IJCV) ...

Vision-Language Alignment Learning Under Affinity and Divergence Principles for Few-Shot Out-of-Distribution Generalization. Lin Zhu; Weihan Yin; Nanyang Ye.

Vision-language alignment learning under affinity and divergence principles for few-shot out-of-distribution generalization. L Zhu, W Yin, Y Yang, F Wu, Z Zeng, ...

Besides, we introduce affinity and divergence principles to further mitigate overfitting during the vision-language aligning process by increasing class ...

Vision-Language Alignment Learning Under Affinity and Divergence Principles for Few-Shot Out-of-Distribution Generalization · Lin ZhuWeihan Yin +6 authors

We investigate the Non-I.I.D problem in image classification and give an index NI to measure the degree of distribution shift.