PatchMix Augmentation to Identify Causal Features in Few-shot Learning

by   Chengming Xu, et al.

The task of Few-shot learning (FSL) aims to transfer the knowledge learned from base categories with sufficient labelled data to novel categories with scarce known information. It is currently an important research question and has great practical values in the real-world applications. Despite extensive previous efforts are made on few-shot learning tasks, we emphasize that most existing methods did not take into account the distributional shift caused by sample selection bias in the FSL scenario. Such a selection bias can induce spurious correlation between the semantic causal features, that are causally and semantically related to the class label, and the other non-causal features. Critically, the former ones should be invariant across changes in distributions, highly related to the classes of interest, and thus well generalizable to novel classes, while the latter ones are not stable to changes in the distribution. To resolve this problem, we propose a novel data augmentation strategy dubbed as PatchMix that can break this spurious dependency by replacing the patch-level information and supervision of the query images with random gallery images from different classes from the query ones. We theoretically show that such an augmentation mechanism, different from existing ones, is able to identify the causal features. To further make these features to be discriminative enough for classification, we propose Correlation-guided Reconstruction (CGR) and Hardness-Aware module for instance discrimination and easier discrimination between similar classes. Moreover, such a framework can be adapted to the unsupervised FSL scenario.


page 2

page 5

page 11

page 12

page 15


Instance-level Few-shot Learning with Class Hierarchy Mining

Few-shot learning is proposed to tackle the problem of scarce training d...

Few-Shot Learning with Part Discovery and Augmentation from Unlabeled Images

Few-shot learning is a challenging task since only few instances are giv...

Adversarial Feature Hallucination Networks for Few-Shot Learning

The recent flourish of deep learning in various tasks is largely accredi...

Semantic-Based Few-Shot Learning by Interactive Psychometric Testing

Few-shot classification tasks aim to classify images in query sets based...

Task-Independent Knowledge Makes for Transferable Representations for Generalized Zero-Shot Learning

Generalized Zero-Shot Learning (GZSL) targets recognizing new categories...

Supercharging Imbalanced Data Learning With Causal Representation Transfer

Dealing with severe class imbalance poses a major challenge for real-wor...

Wave-SAN: Wavelet based Style Augmentation Network for Cross-Domain Few-Shot Learning

Previous few-shot learning (FSL) works mostly are limited to natural ima...

Please sign up or login with your details

Forgot password? Click here to reset