A Simple Data Mixing Prior for Improving Self-Supervised Learning

• URL: http://arxiv.org/abs/2206.07692v1
• Date: Wed, 15 Jun 2022 17:40:56 GMT
• Title: A Simple Data Mixing Prior for Improving Self-Supervised Learning
• Abstract summary: We propose SDMP, short for $textbfS$imple $textbfD$ata $textbfM$ixing $textbfP$rior. Our experiments verify that the proposed SDMP enables data mixing to help a set of self-supervised learning frameworks achieve better accuracy and out-of-distribution robustness.
• Score: 52.28244748245043
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same source images are intrinsically related to each other, we hereby propose SDMP, short for $\textbf{S}$imple $\textbf{D}$ata $\textbf{M}$ixing $\textbf{P}$rior, to capture this straightforward yet essential prior, and position such mixed images as additional $\textbf{positive pairs}$ to facilitate self-supervised representation learning. Our experiments verify that the proposed SDMP enables data mixing to help a set of self-supervised learning frameworks (e.g., MoCo) achieve better accuracy and out-of-distribution robustness. More notably, our SDMP is the first method that successfully leverages data mixing to improve (rather than hurt) the performance of Vision Transformers in the self-supervised setting. Code is publicly available at https://github.com/OliverRensu/SDMP

Related papers

• Improving Adversarial Robustness of Masked Autoencoders via Test-time Frequency-domain Prompting [133.55037976429088]
  We investigate the adversarial robustness of vision transformers equipped with BERT pretraining (e.g., BEiT, MAE) A surprising observation is that MAE has significantly worse adversarial robustness than other BERT pretraining methods. We propose a simple yet effective way to boost the adversarial robustness of MAE.
  arXiv  Detail & Related papers  (2023-08-20T16:27:17Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• GuidedMixup: An Efficient Mixup Strategy Guided by Saliency Maps [6.396288020763144]
  We propose GuidedMixup, which aims to retain the salient regions in mixup images with low computational overhead. We develop an efficient pairing algorithm that pursues to minimize the conflict of salient regions of paired images. Experiments on several datasets demonstrate that GuidedMixup provides a good trade-off between augmentation overhead and generalization performance.
  arXiv  Detail & Related papers  (2023-06-29T00:55:51Z)
• Inter-Instance Similarity Modeling for Contrastive Learning [22.56316444504397]
  We propose a novel image mix method, PatchMix, for contrastive learning in Vision Transformer (ViT) Compared to the existing sample mix methods, our PatchMix can flexibly and efficiently mix more than two images. Our proposed method significantly outperforms the previous state-of-the-art on both ImageNet-1K and CIFAR datasets.
  arXiv  Detail & Related papers  (2023-06-21T13:03:47Z)
• Exploring the Limits of Deep Image Clustering using Pretrained Models [1.1060425537315088]
  We present a methodology that learns to classify images without labels by leveraging pretrained feature extractors. We propose a novel objective that learns associations between image features by introducing a variant of pointwise mutual information together with instance weighting.
  arXiv  Detail & Related papers  (2023-03-31T08:56:29Z)
• Mixed Autoencoder for Self-supervised Visual Representation Learning [95.98114940999653]
  Masked Autoencoder (MAE) has demonstrated superior performance on various vision tasks via randomly masking image patches and reconstruction. This paper studies the prevailing mixing augmentation for MAE.
  arXiv  Detail & Related papers  (2023-03-30T05:19:43Z)
• 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)
• 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)
• Mixup Without Hesitation [38.801366276601414]
  We propose mixup Without hesitation (mWh), a concise, effective, and easy-to-use training algorithm. mWh strikes a good balance between exploration and exploitation by gradually replacing mixup with basic data augmentation. Our code is open-source and available at https://github.com/yuhao318318/mWh.
  arXiv  Detail & Related papers  (2021-01-12T08:11:08Z)
• Mixup-Transformer: Dynamic Data Augmentation for NLP Tasks [75.69896269357005]
  Mixup is the latest data augmentation technique that linearly interpolates input examples and the corresponding labels. In this paper, we explore how to apply mixup to natural language processing tasks. We incorporate mixup to transformer-based pre-trained architecture, named "mixup-transformer", for a wide range of NLP tasks.
  arXiv  Detail & Related papers  (2020-10-05T23:37:30Z)

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.