An Embarrassingly Simple Baseline to One-Shot Learning - Crossminds
CrossMind.ai logo

An Embarrassingly Simple Baseline to One-Shot Learning

Sep 29, 2020
|
36 views
Details
Authors: Chen Liu, Chengming Xu, Yikai Wang, Li Zhang, Yanwei Fu Description: In this paper, we propose an embarrassingly simple approach for one-shot learning. Our insight is that the one-shot tasks have domain gap to the network pretrained tasks and thus some features from the pretrained network are not relevant, or harmful to the specific one-shot task. Therefore, we propose to directly prune the features from the pretrained network for a specific one-shot task rather than update it via an optimized scheme with complex network structure. Without bells and whistles, our simple yet effective method achieves leading performances on miniImageNet (60.63%) and tieredImageNet (69.02%) for 5-way one-shot setting. The best trial can hit to 66.83% on miniImageNet and 74.04% on tieredImageNet, establishing a new state-of-the-art. We strongly advocate that our method can serve as a strong baseline for one-shot learning. The codes and trained models will be released at http://github.com/corwinliu9669/embarrassingly-simple-baseline.

Comments
loading...
Reactions (0) | Note
    📝 No reactions yet
    Be the first one to share your thoughts!
loading...
Recommended