Abstract | ||
---|---|---|
Recently, few-shot learning has attracted more and more attention. Generally, the fine-tuning-based few-shot learning framework contains two stages: i) In the pre-training stage, using base data to train the feature extractor; ii) In the meta-testing stage, using a well-trained feature extractor to extract embedding features of novel data and designing a base learner to predict the labels. Due to the diverse categories of base and novel data, it is challenging for the feature extractor trained in the pre-training stage to adapt to novel data, which will result in an embedding-mismatch problem. This paper proposes Task-specific Discriminative Embeddings for Few-shot Learning (TDE-FSL) to solve the embedding-mismatch problem. Specifically, we embed the dictionary learning method into the few-shot learning framework to map the feature embeddings to a more discriminative subspace to adapt to the specific task. Moreover, we extend the self-training framework to our approach to fully utilize the unlabeled data. Finally, we evaluate the TDE-FSL on five benchmark image datasets, such as mini-Imagenet, tiered-Imagenet, CIFAR-FS, FC100, and CUB dataset. The experimental results show that the performance of our proposed TDE-FSL achieves a significant improvement. |
Year | DOI | Venue |
---|---|---|
2022 | 10.1016/j.neucom.2022.02.073 | Neurocomputing |
Keywords | DocType | Volume |
Few-shot learning,Dictionary learning,Task-specific discriminative embeddings | Journal | 488 |
ISSN | Citations | PageRank |
0925-2312 | 0 | 0.34 |
References | Authors | |
0 | 6 |
Name | Order | Citations | PageRank |
---|---|---|---|
Lei Xing | 1 | 102 | 23.72 |
Shuai Shao | 2 | 3 | 2.41 |
Weifeng Liu | 3 | 87 | 13.82 |
Anxun Han | 4 | 0 | 0.34 |
Xiangshuai Pan | 5 | 0 | 0.34 |
Bao-Di Liu | 6 | 166 | 27.34 |