paper-with-me

Papers

PatchMix Augmentation to Identify Causal Features in Few-shot Learning

2022-11-29 · Chengming Xu, Chen Liu, Xinwei Sun, Siqian Yang, Yabiao Wang, Chengjie Wang, Yanwei Fu

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.

📄 PDF Abstract BibTeX arXiv:2211.16019

Code (0)

등록된 구현이 없습니다.

Tasks

Data AugmentationFew-Shot LearningSelection bias

Methods 이 논문이 사용한 방법론

BASE 설명 없음

Similar Papers 제목 키워드 기반

PointPatchMix: Point Cloud Mixing with Patch Scoring

2023-03-12 · Yi Wang, Jiaze Wang, Jinpeng Li, Zixu Zhao 외

Data augmentation is an effective regularization strategy for mitigating overfitting in deep neural networks, and it plays a crucial role in 3D vision tasks, where the point cloud data is relatively limited. While mixing…

Data Augmentation

Evolving Image Compositions for Feature Representation Learning

2021-06-16 · Paola Cascante-Bonilla, Arshdeep Sekhon, Yanjun Qi, Vicente Ordonez

Convolutional neural networks for visual recognition require large amounts of training samples and usually benefit from data augmentation. This paper proposes PatchMix, a data augmentation method that creates new samples…

Data AugmentationRepresentation LearningTransfer Learning

Shuffle PatchMix Augmentation with Confidence-Margin Weighted Pseudo-Labels for Enhanced Source-Free Domain Adaptation

2025-05-30 · Prasanna Reddy Pulakurthi, Majid Rabbani, Jamison Heard, Sohail Dianat 외

This work investigates Source-Free Domain Adaptation (SFDA), where a model adapts to a target domain without access to source data. A new augmentation technique, Shuffle PatchMix (SPM), and a novel reweighting strategy a…

Data AugmentationDomain AdaptationPseudo LabelSource-Free Domain Adaptation

Semantically Proportional Patchmix for Few-Shot Learning

2022-02-17 · Jingquan Wang, Jing Xu, Yu Pan, Zenglin Xu

Few-shot learning aims to classify unseen classes with only a limited number of labeled data. Recent works have demonstrated that training models with a simple transfer learning strategy can achieve competitive results i…

Few-Shot LearningTransfer Learning

PatchMixer: A Patch-Mixing Architecture for Long-Term Time Series Forecasting

2023-10-01 · Zeying Gong, Yujin Tang, Junwei Liang

Although the Transformer has been the dominant architecture for time series forecasting tasks in recent years, a fundamental challenge remains: the permutation-invariant self-attention mechanism within Transformers leads…

Time SeriesTime Series Forecasting