12 citations · 27 across the 9 of their papers we have counts for
3 papers · 1 filter
Generalization Beyond Feature Alignment: Concept Activation-Guided Contrastive Learning
Yibing Liu, Chris Xing Tian, Haoliang Li +1
Learning invariant representations via contrastive learning has seen state-of-the-art performance in domain generalization (DG). Despite such success, in this paper, we find that i…
A Unified End-to-End Retriever-Reader Framework for Knowledge-based VQA
Yangyang Guo, Liqiang Nie, Yongkang Wong +3
Knowledge-based Visual Question Answering (VQA) expects models to rely on external knowledge for robust answer prediction. Though significant it is, this paper discovers several le…
Rethinking Attention-Model Explainability through Faithfulness Violation Test
Yibing Liu, Haoliang Li, Yangyang Guo +3
Attention mechanisms are dominating the explainability of deep models. They produce probability distributions over the input, which are widely deemed as feature-importance indicato…