On the Importance of Distractors for Few-Shot Classification

Rajshekhar Das, Yu-Xiong Wang, Jose M. F. Moura; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 9030-9040


Few-shot classification aims at classifying categories of a novel task by learning from just a few (typically, 1 to 5) labeled examples. An effective approach to few-shot classification involves a prior model trained on a large-sample base domain, which is then finetuned over the novel few-shot task to yield generalizable representations. However, task-specific finetuning is prone to overfitting due to the lack of enough training examples. To alleviate this issue, we propose a new finetuning approach based on contrastive learning that reuses unlabelled examples from the base domain in the form of distractors. Unlike the nature of unlabelled data used in prior works, distractors belong to classes that do not overlap with the novel categories. We demonstrate for the first time that the inclusion of such distractors can significantly boost few-shot generalization. Our technical novelty includes a stochastic pairing of examples sharing the same category in the few-shot task and a weighting term that controls the relative influence of task-specific negatives and distractors. An important aspect of our finetuning objective is that it is agnostic to distractor labels and hence applicable to various base domain settings. More precisely, compared to state-of-the-art approaches, our method shows accuracy gains of up to 12% in cross-domain and up to 5% in unsupervised prior-learning settings. Our code is available at https://github.com/quantacode/Contrastive-Finetuning.git

Related Material

[pdf] [supp] [arXiv]
@InProceedings{Das_2021_ICCV, author = {Das, Rajshekhar and Wang, Yu-Xiong and Moura, Jose M. F.}, title = {On the Importance of Distractors for Few-Shot Classification}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {9030-9040} }