Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation
arXiv:2006.07585
Abstract
Despite the huge progress in scene graph generation in recent years, its long-tail distribution in object relationships remains a challenging and pestering issue. Existing methods largely rely on either 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; and (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.
References in corpus (6)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Visual Relationship Detection with Language Priors
- Massive Exploration of Neural Machine Translation Architectures
- Knowledge-Embedded Routing Network for Scene Graph Generation
- Scene Graph Generation with External Knowledge and Image Reconstruction
- Few-Shot Learning via Saliency-guided Hallucination of Samples