30/11/2020

Synthesizing the Unseen for Zero-shot Object Detection

Nasir Hayat, Munawar Hayat, Shafin Rahman, Salman Khan, Syed Waqas Zamir, Fahad Shahbaz Khan

Keywords:

Abstract Paper Similar Papers

Abstract: The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never visualized during training, the detection model is skewed towards seen content, thereby labeling unseen as background or a seen class. In this work, we propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain. Consequently, the major challenge becomes, how to accurately synthesize unseen objects merely using their class semantics? Towards this ambitious goal, we propose a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them. Further, using a unified model, we ensure the synthesized features have high diversity that represents the intra-class differences and variable localization precision in the detected bounding boxes. We test our approach on three object detection benchmarks, PASCAL VOC, MSCOCO, and ILSVRC detection, under both conventional and generalized settings, showing impressive gains over the state-of-the-art methods.

The video of this talk cannot be embedded. You can watch it here:
https://accv2020.github.io/miniconf/poster_591.html
(Link will open in new window)
 0
 0
 0
 0
  Share    
This is an embedded video. Talk and the respective paper are published at ACCV 2020 virtual conference. If you are one of the authors of the paper and want to manage your upload, see the question "My papertalk has been externally embedded..." in the FAQ section.

Comments

Post Comment
no comments yet
code of conduct: tbd Characters remaining: 140

Similar Papers

 0
 0
 0
 0
 14:57 
 0
 0
 0
 0
 3:11 
 0
 0
 0
 0
 8:46 
 0
 0
 0
 0
 4:45 
 0
 0
 0
 0
 3:02 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 2:48 
 0
 0
 0
 0
 0:58 
 0
 0
 0
 0
 1:02 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 16:22 
 0
 0
 0
 0
 7:26 
 0
 0
 0
 0
 4:59 
 0
 0
 0
 0
 11:09 
 0
 0
 0
 0
 1:00 
 0
 0
 0
 0
 4:57 
 0
 0
 0
 0
 15:15 
 0
 0
 0
 0
 14:56 
 0
 0
 0
 0
 12:10 
 0
 0
 0
 0
 5:18 
 0
 0
 0
 0
 1:01 
 0
 0
 0
 0
 8:31 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 3:22 
 0
 0
 0
 0
 3:20 
 0
 0
 0
 0
 8:08 
 0
 0
 0
 0
 12:38 
 0
 0
 0
 0
 10:33 
 0
 0
 0
 0
 9:57 
 0
 0
 0
 0
 3:24 
 0
 0
 0
 0
 7:50 
 0
 0
 0
 0
 4:56 
 0
 0
 0
 0
 15:00 
 0
 0
 0
 0
 2:47 
 0
 0
 0
 0
 14:20 
 0
 0
 0
 0
 5:11 
 0
 0
 0
 0
 10:03 
 0
 0
 0
 0
 4:59