Timezone: »

 
Poster
Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognition
Satoshi Tsutsui · Yanwei Fu · David Crandall

Wed Dec 11 05:00 PM -- 07:00 PM (PST) @ East Exhibition Hall B + C #22
in Algorithms -- Few-Shot Learning »

This paper studies the task of one-shot fine-grained recognition, which suffers from the problem of data scarcity of novel fine-grained classes. To alleviate this problem, a off-the-shelf image generator can be applied to synthesize additional images to help one-shot learning. However, such synthesized images may not be helpful in one-shot fine-grained recognition, due to a large domain discrepancy between synthesized and original images. To this end, this paper proposes a meta-learning framework to reinforce the generated images by original images so that these images can facilitate one-shot learning. Specifically, the generic image generator is updated by few training instances of novel classes; and a Meta Image Reinforcing Network (MetaIRNet) is proposed to conduct one-shot fine-grained recognition as well as image reinforcement. The model is trained in an end-to-end manner, and our experiments demonstrate consistent improvement over baseline on one-shot fine-grained image classification benchmarks.

Keywords: Generative Models · Algorithms · Few-Shot Learning · Applications -> Computer Vision; Applications -> Object Recognition; Deep Learning
[ Paper]  [ Slides] 

Author Information

Satoshi Tsutsui (Indiana University)
Yanwei Fu (Fudan University, Shanghai;)
David Crandall (Indiana University)

More from the Same Authors