REVIEW 5 cited by
SaliencyMix: A Saliency Guided Data Augmentation Strategy for Better Regularization
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Advanced data augmentation strategies have widely been studied to improve the generalization ability of deep learning models. Regional dropout is one of the popular solutions that guides the model to focus on less discriminative parts by randomly removing image regions, resulting in improved regularization. However, such information removal is undesirable. On the other hand, recent strategies suggest to randomly cut and mix patches and their labels among training images, to enjoy the advantages of regional dropout without having any pointless pixel in the augmented images. We argue that such random selection strategies of the patches may not necessarily represent sufficient information about the corresponding object and thereby mixing the labels according to that uninformative patch enables the model to learn unexpected feature representation. Therefore, we propose SaliencyMix that carefully selects a representative image patch with the help of a saliency map and mixes this indicative patch with the target image, thus leading the model to learn more appropriate feature representation. SaliencyMix achieves the best known top-1 error of 21.26% and 20.09% for ResNet-50 and ResNet-101 architectures on ImageNet classification, respectively, and also improves the model robustness against adversarial perturbations. Furthermore, models that are trained with SaliencyMix help to improve the object detection performance. Source code is available at https://github.com/SaliencyMix/SaliencyMix.
Forward citations
Cited by 5 Pith papers
-
MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentation
Saliency-guided diffusion mixing that preserves Grad-CAM-highlighted diagnostic regions improves medical image classification accuracy and AUC across four public datasets.
-
Towards Understanding Why Data Augmentation Improves Generalization
Data augmentation improves generalization through two mechanisms, partial semantic feature removal and feature mixing, which respectively promote diverse and robust feature learning.
-
Improving Object Detection by Modifying Synthetic Data with Explainable AI
SHAP-guided edits to synthetic 3D vehicle models improved infrared vehicle detection mAP50 from 94.6% to 96.1%, though the gain is not shown to be independent of test-set inspection.
-
An approach based on class activation maps for investigating the effects of data augmentation on neural networks for image classification
A Grad-CAM-based methodology with similarity metrics reveals that data augmentation techniques affect learned attention patterns in distinct clusters, but individual differences are small.
-
MediAug: Exploring Visual Augmentation in Medical Imaging
A benchmark of six mix-based augmentations on two medical datasets finds different best methods per dataset and backbone, but the results are undermined by missing error bars and table inconsistencies.
Discussion (0). Continue with ORCID to comment.