Learning from the Scene and Borrowing from the Rich: Tackling the Long Tail in Scene Graph Generation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Graph GenerationObjectScene Graph GenerationTransfer LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Detecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling
This work presents a new resource for borrowing identification and analyzes the performance and errors of several models on this task. We introduce a new annotated corpus of Spanish newswire rich in unassimilated lexical…
Word EmbeddingsDetecting Unassimilated Borrowings in Spanish: An Annotated Corpus and Approaches to Modeling
This work presents a new resource for borrowing identification and analyzes the performance and errors of several models on this task. We introduce a new annotated corpus of Spanish newswire rich in unassimilated lexical…
Word EmbeddingsLong-tail Internet photo reconstruction
Internet photo collections exhibit an extremely long-tailed distribution: a few famous landmarks are densely photographed and easily reconstructed in 3D, while most real-world sites are represented with sparse, noisy, un…
RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition
The visual relationship recognition (VRR) task aims at understanding the pairwise visual relationships between interacting objects in an image. These relationships typically have a long-tail distribution due to their com…
Image CaptioningObject RecognitionQuestion AnsweringRelation+5RefinedFields: Radiance Fields Refinement for Unconstrained Scenes
Modeling large scenes from unconstrained images has proven to be a major challenge in computer vision. Existing methods tackling in-the-wild scene modeling operate in closed-world settings, where no conditioning on prior…
Neural RenderingNovel View Synthesis