eduzhai > Applied Sciences > Engineering >

Learning from the Scene and Borrowing from the Rich Tackling the Long Tail in Scene Graph Generation

  • Save

... pages left unread,continue reading

Document pages: 7 pages

Abstract: Despite the huge progress in scene graph generation in recent years, itslong-tail distribution in object relationships remains a challenging andpestering issue. Existing methods largely rely on either external knowledge orstatistical bias information to alleviate this problem. In this paper, wetackle this issue from another two aspects: (1) scene-object interaction aimingat learning specific knowledge from a scene via an additive attentionmechanism; and (2) long-tail knowledge transfer which tries to transfer therich knowledge learned from the head into the tail. Extensive experiments onthe benchmark dataset Visual Genome on three tasks demonstrate that our methodoutperforms current state-of-the-art competitors.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×