paper-with-me

홈 › Papers

Provable Benefit of Cutout and CutMix for Feature Learning

2024-10-31 · Junsoo Oh, Chulhee Yun

Patch-level data augmentation techniques such as Cutout and CutMix have demonstrated significant efficacy in enhancing the performance of vision tasks. However, a comprehensive theoretical understanding of these methods remains elusive. In this paper, we study two-layer neural networks trained using three distinct methods: vanilla training without augmentation, Cutout training, and CutMix training. Our analysis focuses on a feature-noise data model, which consists of several label-dependent features of varying rarity and label-independent noises of differing strengths. Our theorems demonstrate that Cutout training can learn low-frequency features that vanilla training cannot, while CutMix training can learn even rarer features that Cutout cannot capture. From this, we establish that CutMix yields the highest test accuracy among the three. Our novel analysis reveals that CutMix training makes the network learn all features and noise vectors "evenly" regardless of the rarity and strength, which provides an interesting insight into understanding patch-level augmentation.

📄 PDF Abstract BibTeX arXiv:2410.23672

Code (0)

등록된 구현이 없습니다.

Tasks

Data Augmentation

Methods 이 논문이 사용한 방법론

Cutout Cutout is an image augmentation and regularization technique that randomly masks out square regions of input during training. and can be used to improve the robustness and…
CutMix CutMix is an image data augmentation strategy. Instead of simply removing pixels as in Cutout, we replace the removed regions with…

Similar Papers 제목 키워드 기반

Towards Understanding Why Data Augmentation Improves Generalization

2025-02-13 · Jingyang Li, Jiachun Pan, Kim-Chuan Toh, Pan Zhou

Data augmentation is a cornerstone technique in deep learning, widely used to improve model generalization. Traditional methods like random cropping and color jittering, as well as advanced techniques such as CutOut, Mix…

Data Augmentation

Studying the Impact of Augmentations on Medical Confidence Calibration

2023-08-23 · Adrit Rao, Joon-Young Lee, Oliver Aalami

The clinical explainability of convolutional neural networks (CNN) heavily relies on the joint interpretation of a model's predicted diagnostic label and associated confidence. A highly certain or uncertain model can sig…

Decision MakingDiagnostic

Attentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification

2020-03-29 · Devesh Walawalkar, Zhiqiang Shen, Zechun Liu, Marios Savvides

Convolutional neural networks (CNN) are capable of learning robust representation with different regularization methods and activations as convolutional layers are spatially correlated. Based on this property, a large va…

Data AugmentationDescriptiveGeneral Classificationimage-classification+1

TextAug: Test time Text Augmentation for Multimodal Person Re-identification

2023-12-04 · Mulham Fawakherji, Eduard Vazquez, Pasquale Giampa, Binod Bhattarai

Multimodal Person Reidentification is gaining popularity in the research community due to its effectiveness compared to counter-part unimodal frameworks. However, the bottleneck for multimodal deep learning is the need f…

Data AugmentationMultimodal Deep LearningPerson Re-IdentificationSentence+1

Semi-supervised semantic segmentation needs strong, varied perturbations

2019-06-05 · Geoff French, Samuli Laine, Timo Aila, Michal Mackiewicz 외

Consistency regularization describes a class of approaches that have yielded ground breaking results in semi-supervised classification problems. Prior work has established the cluster assumption - under which the data di…

General ClassificationSegmentationSemantic SegmentationSemi-Supervised Semantic Segmentation