Non-Probabilistic Cosine Similarity Loss for Few-Shot Image Classification

Cited 0 time in webofscience Cited 0 time in scopus
  • Hit : 28
  • Download : 0
A few-shot image classification problem aims to recognize previously unseen objects with a small amount of data. Many works have been offered to solve the problem, while a simple transfer learning method with the cosine similarity based cross-entropy loss is still powerful compared with other methods. To improve the performance, we propose a novel Non-Probabilistic Cosine similarity (NPC) loss for few-shot classification that can replace the cross-entropy loss with the cosine similarity. A key difference of NPC loss is that it uses values of inputs instead of their probabilities. By simply changing the loss function, our model avoids overfitting on a training set and performs well on few-shot tasks. Experimental results show that the model with NPC loss clearly outperforms those with other loss functions and also achieves excellent performance compared with state-of-the-art algorithms on Mini-Imagenet and CUB-200-2011 datasets.
Publisher
The British Machine Vision Association and Society for Pattern Recognition
Issue Date
2020-09-07
Language
English
Citation

The 31st British Machine Vision Conference

URI
http://hdl.handle.net/10203/278752
Appears in Collection
EE-Conference Papers(학술회의논문)
Files in This Item
There are no files associated with this item.

qr_code

  • mendeley

    citeulike


rss_1.0 rss_2.0 atom_1.0