Soft Augmentation for Image Classification

• URL: http://arxiv.org/abs/2211.04625v2
• Date: Tue, 23 Jan 2024 21:24:53 GMT
• Title: Soft Augmentation for Image Classification
• Authors: Yang Liu, Shen Yan, Laura Leal-Taix\'e, James Hays, Deva Ramanan
• Abstract summary: We propose generalizing augmentation with invariant transforms to soft augmentation. We show that soft targets allow for more aggressive data augmentation. We also show that soft augmentations generalize to self-supervised classification tasks.
• Score: 68.71067594724663
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Modern neural networks are over-parameterized and thus rely on strong regularization such as data augmentation and weight decay to reduce overfitting and improve generalization. The dominant form of data augmentation applies invariant transforms, where the learning target of a sample is invariant to the transform applied to that sample. We draw inspiration from human visual classification studies and propose generalizing augmentation with invariant transforms to soft augmentation where the learning target softens non-linearly as a function of the degree of the transform applied to the sample: e.g., more aggressive image crop augmentations produce less confident learning targets. We demonstrate that soft targets allow for more aggressive data augmentation, offer more robust performance boosts, work with other augmentation policies, and interestingly, produce better calibrated models (since they are trained to be less confident on aggressively cropped/occluded examples). Combined with existing aggressive augmentation strategies, soft target 1) doubles the top-1 accuracy boost across Cifar-10, Cifar-100, ImageNet-1K, and ImageNet-V2, 2) improves model occlusion performance by up to $4\times$, and 3) halves the expected calibration error (ECE). Finally, we show that soft augmentation generalizes to self-supervised classification tasks. Code available at https://github.com/youngleox/soft_augmentation

Related papers

• Fourier-basis Functions to Bridge Augmentation Gap: Rethinking Frequency Augmentation in Image Classification [3.129187821625805]
  Auxiliary Fourier-basis Augmentation (AFA) is a technique targeting augmentation in the frequency domain and filling the augmentation gap left by visual augmentations. Our results show that AFA benefits the robustness of models against common corruptions, OOD generalization, and consistency of performance of models against increasing perturbations, with negligible deficit to the standard performance of models.
  arXiv  Detail & Related papers  (2024-03-04T11:30:02Z)
• DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection [77.6648187359111]
  We propose a novel data augmentation method, named textbfDualAug, to keep the augmentation in distribution as much as possible at a reasonable time and computational cost. Experiments on supervised image classification benchmarks show that DualAug improve various automated data augmentation method.
  arXiv  Detail & Related papers  (2023-10-12T08:55:10Z)
• SAGE: Saliency-Guided Mixup with Optimal Rearrangements [22.112463794733188]
  Saliency-Guided Mixup with Optimal Rearrangements (SAGE) SAGE creates new training examples by rearranging and mixing image pairs using visual saliency as guidance. We demonstrate on CIFAR-10 and CIFAR-100 that SAGE achieves better or comparable performance to the state of the art while being more efficient.
  arXiv  Detail & Related papers  (2022-10-31T19:45:21Z)
• Masked Autoencoders are Robust Data Augmentors [90.34825840657774]
  Regularization techniques like image augmentation are necessary for deep neural networks to generalize well. We propose a novel perspective of augmentation to regularize the training process. We show that utilizing such model-based nonlinear transformation as data augmentation can improve high-level recognition tasks.
  arXiv  Detail & Related papers  (2022-06-10T02:41:48Z)
• Improving Model Generalization by Agreement of Learned Representations from Data Augmentation [19.286766429954174]
  In computer vision, data augmentation techniques such as CutOut, MixUp, and CutMix demonstrated state-of-the-art (SOTA) results. We call our proposed method Agreement Maximization or simply AgMax. We show that AgMax can take advantage of the data augmentation to consistently improve model generalization by a significant margin.
  arXiv  Detail & Related papers  (2021-10-20T12:44:52Z)
• Augmentation Pathways Network for Visual Recognition [61.33084317147437]
  This paper introduces Augmentation Pathways (AP) to stabilize training on a much wider range of augmentation policies. AP tames heavy data augmentations and stably boosts performance without a careful selection among augmentation policies. Experimental results on ImageNet benchmarks demonstrate the compatibility and effectiveness on a much wider range of augmentations.
  arXiv  Detail & Related papers  (2021-07-26T06:54:53Z)
• When Vision Transformers Outperform ResNets without Pretraining or Strong Data Augmentations [111.44860506703307]
  Vision Transformers (ViTs) and existing VisionNets signal efforts on replacing hand-wired features or inductive throughputs with general-purpose neural architectures. This paper investigates ViTs and Res-Mixers from the lens of loss geometry, intending to improve the models' data efficiency at training and inference. We show that the improved robustness attributes to sparser active neurons in the first few layers. The resultant ViTs outperform Nets of similar size and smoothness when trained from scratch on ImageNet without large-scale pretraining or strong data augmentations.
  arXiv  Detail & Related papers  (2021-06-03T02:08:03Z)
• InAugment: Improving Classifiers via Internal Augmentation [14.281619356571724]
  We present a novel augmentation operation, that exploits image internal statistics. We show improvement over state-of-the-art augmentation techniques. We also demonstrate an increase for ResNet50 and EfficientNet-B3 top-1's accuracy on the ImageNet dataset.
  arXiv  Detail & Related papers  (2021-04-08T15:37:21Z)
• Reweighting Augmented Samples by Minimizing the Maximal Expected Loss [51.2791895511333]
  We construct the maximal expected loss which is the supremum over any reweighted loss on augmented samples. Inspired by adversarial training, we minimize this maximal expected loss and obtain a simple and interpretable closed-form solution. The proposed method can generally be applied on top of any data augmentation methods.
  arXiv  Detail & Related papers  (2021-03-16T09:31:04Z)
• On the Generalization Effects of Linear Transformations in Data Augmentation [32.01435459892255]
  Data augmentation is a powerful technique to improve performance in applications such as image and text classification tasks. We study a family of linear transformations and study their effects on the ridge estimator in an over-parametrized linear regression setting. We propose an augmentation scheme that searches over the space of transformations by how uncertain the model is about the transformed data.
  arXiv  Detail & Related papers  (2020-05-02T04:10:21Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.