Provable Benefit of Cutout and CutMix for Feature Learning
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Towards Understanding Why Data Augmentation Improves Generalization
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 AugmentationStudying the Impact of Augmentations on Medical Confidence Calibration
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 MakingDiagnosticAttentive CutMix: An Enhanced Data Augmentation Approach for Deep Learning Based Image Classification
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+1TextAug: Test time Text Augmentation for Multimodal Person Re-identification
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+1Semi-supervised semantic segmentation needs strong, varied perturbations
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