Long-tail distribution in object relationships remains a challenging and pestering issue . Existing methods largely rely on external knowledge or statistical bias information to alleviate this problem . In this paper, we tackle this issue from another two aspects: (1) scene-object interaction aiming at learning specific knowledge from a scene via an additive attention mechanism . (2) long-tail knowledge transfer which tries to transfer the rich knowledge learned from the head into the tail . Extensive experiments on the benchmark dataset Visual Genome on three tasks demonstrate that our method outperforms current state-of-the-art competitors .

Links: PDF - Abstract

Code :


Keywords : tail - scene - knowledge - long - learning -

Leave a Reply

Your email address will not be published. Required fields are marked *