FMix: Enhancing Mixed Sample Data Augmentation

• URL: http://arxiv.org/abs/2002.12047v3
• Date: Sun, 28 Feb 2021 14:47:36 GMT
• Title: FMix: Enhancing Mixed Sample Data Augmentation
• Authors: Ethan Harris, Antonia Marcu, Matthew Painter, Mahesan Niranjan, Adam Pr\"ugel-Bennett, Jonathon Hare
• Abstract summary: Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent years. We show that MixUp distorts learned functions in a way that CutMix does not. We propose FMix, an MSDA that uses random binary masks obtained by applying a threshold to low frequency images.
• Score: 5.820517596386667
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Mixed Sample Data Augmentation (MSDA) has received increasing attention in recent years, with many successful variants such as MixUp and CutMix. By studying the mutual information between the function learned by a VAE on the original data and on the augmented data we show that MixUp distorts learned functions in a way that CutMix does not. We further demonstrate this by showing that MixUp acts as a form of adversarial training, increasing robustness to attacks such as Deep Fool and Uniform Noise which produce examples similar to those generated by MixUp. We argue that this distortion prevents models from learning about sample specific features in the data, aiding generalisation performance. In contrast, we suggest that CutMix works more like a traditional augmentation, improving performance by preventing memorisation without distorting the data distribution. However, we argue that an MSDA which builds on CutMix to include masks of arbitrary shape, rather than just square, could further prevent memorisation whilst preserving the data distribution in the same way. To this end, we propose FMix, an MSDA that uses random binary masks obtained by applying a threshold to low frequency images sampled from Fourier space. These random masks can take on a wide range of shapes and can be generated for use with one, two, and three dimensional data. FMix improves performance over MixUp and CutMix, without an increase in training time, for a number of models across a range of data sets and problem settings, obtaining a new single model state-of-the-art result on CIFAR-10 without external data. Finally, we show that a consequence of the difference between interpolating MSDA such as MixUp and masking MSDA such as FMix is that the two can be combined to improve performance even further. Code for all experiments is provided at https://github.com/ecs-vlc/FMix .

Related papers

• SUMix: Mixup with Semantic and Uncertain Information [41.99721365685618]
  Mixup data augmentation approaches have been applied for various tasks of deep learning. We propose a novel approach named SUMix to learn the mixing ratio as well as the uncertainty for the mixed samples during the training process.
  arXiv  Detail & Related papers  (2024-07-10T16:25:26Z)
• TransformMix: Learning Transformation and Mixing Strategies from Data [20.79680733590554]
  We propose an automated approach, TransformMix, to learn better transformation and mixing augmentation strategies from data. We demonstrate the effectiveness of TransformMix on multiple datasets in transfer learning, classification, object detection, and knowledge distillation settings.
  arXiv  Detail & Related papers  (2024-03-19T04:36:41Z)
• SMMix: Self-Motivated Image Mixing for Vision Transformers [65.809376136455]
  CutMix is a vital augmentation strategy that determines the performance and generalization ability of vision transformers (ViTs) Existing CutMix variants tackle this problem by generating more consistent mixed images or more precise mixed labels. We propose an efficient and effective Self-Motivated image Mixing method (SMMix) which motivates both image and label enhancement by the model under training itself.
  arXiv  Detail & Related papers  (2022-12-26T00:19:39Z)
• C-Mixup: Improving Generalization in Regression [71.10418219781575]
  Mixup algorithm improves generalization by linearly interpolating a pair of examples and their corresponding labels. We propose C-Mixup, which adjusts the sampling probability based on the similarity of the labels. C-Mixup achieves 6.56%, 4.76%, 5.82% improvements in in-distribution generalization, task generalization, and out-of-distribution robustness, respectively.
  arXiv  Detail & Related papers  (2022-10-11T20:39:38Z)
• DoubleMix: Simple Interpolation-Based Data Augmentation for Text Classification [56.817386699291305]
  This paper proposes a simple yet effective data augmentation approach termed DoubleMix. DoubleMix first generates several perturbed samples for each training data. It then uses the perturbed data and original data to carry out a two-step in the hidden space of neural models.
  arXiv  Detail & Related papers  (2022-09-12T15:01:04Z)
• A Unified Analysis of Mixed Sample Data Augmentation: A Loss Function Perspective [24.33244008451489]
  We propose the first unified theoretical analysis of mixed sample data augmentation (MSDA) Our theoretical results show that regardless of the choice of the mixing strategy, MSDA behaves as a pixel-level regularization of the underlying training loss. Our implementation can leverage the advantages of Mixup and CutMix, while our implementation is very efficient.
  arXiv  Detail & Related papers  (2022-08-21T15:54:25Z)
• RandoMix: A mixed sample data augmentation method with multiple mixed modes [12.466162659083697]
  RandoMix is a mixed-sample data augmentation method designed to address robustness and diversity challenges. We evaluate the effectiveness of RandoMix on diverse datasets, including CIFAR-10/100, Tiny-ImageNet, ImageNet, and Google Speech Commands.
  arXiv  Detail & Related papers  (2022-05-18T05:31:36Z)
• MixAugment & Mixup: Augmentation Methods for Facial Expression Recognition [4.273075747204267]
  We propose a new data augmentation strategy which is based on Mixup, called MixAugment. We conduct an extensive experimental study that proves the effectiveness of MixAugment over Mixup and various state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-05-09T17:43:08Z)
• Harnessing Hard Mixed Samples with Decoupled Regularizer [69.98746081734441]
  Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. In this paper, we propose an efficient mixup objective function with a decoupled regularizer named Decoupled Mixup (DM) DM can adaptively utilize hard mixed samples to mine discriminative features without losing the original smoothness of mixup.
  arXiv  Detail & Related papers  (2022-03-21T07:12:18Z)
• SnapMix: Semantically Proportional Mixing for Augmenting Fine-grained Data [124.95585891086894]
  Proposal is called Semantically Proportional Mixing (SnapMix) It exploits class activation map (CAM) to lessen the label noise in augmenting fine-grained data. Our method consistently outperforms existing mixed-based approaches.
  arXiv  Detail & Related papers  (2020-12-09T03:37:30Z)
• Suppressing Mislabeled Data via Grouping and Self-Attention [60.14212694011875]
  Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. This paper proposes a conceptually simple yet efficient training block, termed as Attentive Feature Mixup (AFM) It allows paying more attention to clean samples and less to mislabeled ones via sample interactions in small groups.
  arXiv  Detail & Related papers  (2020-10-29T13:54:16Z)

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.