Cross-domain Few-shot Classification via Invariant-content Feature Reconstruction

Hongduan Tian, Feng Liu, Ka Chun Cheung, Zhen Fang, Simon See, Tongliang Liu, Bo Han

Primary Area: transfer learning, meta learning, and lifelong learning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: cross-domain, few-shot classification, invariant features, computer vision, deep learning

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract: In \emph{cross-domain few-shot classification} (CFC), mainstream studies aim to fast train a new module to select or transform features~(a.k.a., the high-level semantic features) for previously unseen domains with a few labeled training data available on top of a powerful pre-trained model. These studies usually \emph{assume} that high-level semantic features are shared across these domains, and only simple feature selection or transformations are enough to adapt features to those unseen domains. However, in this paper, we find that the simply transformed features are too general to fully cover the key content features regarding each class. Thus, we propose \emph{invariant-content feature reconstruction} (IFR) to train a simple module that simultaneously consider high-level and fine-grained invariant-content features for the previously unseen domains. Specifically, the fine-grained invariant-content features are considered as a set of \emph{informative} and \emph{discriminative} features learned from a few labeled training data of tasks sampled from unseen domains, and are extracted by retrieving features that are invariant to style modifications from a set of content-preserving augmented data in pixel level with an attention module. Extensive experiments on the Meta-Dataset benchmark show that IFR achieves good generalization performance on unseen domains, which demonstrates the effectiveness of the fusion of the high-level features and the fine-grained invariant-content features. Specifically, IFR improves the average accuracy on unseen domains by 1.6\% and 6.5\% respectively under two different CFC experimental settings.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2427