Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation

• URL: http://arxiv.org/abs/2210.12681v1
• Date: Sun, 23 Oct 2022 09:37:47 GMT
• Title: Rethinking Rotation in Self-Supervised Contrastive Learning: Adaptive Positive or Negative Data Augmentation
• Authors: Atsuyuki Miyai, Qing Yu, Daiki Ikami, Go Irie, Kiyoharu Aizawa
• Abstract summary: We propose a novel augmentation strategy, adaptive Positive or Negative Data Augmentation (PNDA) In PNDA, an original and its rotated image are a positive pair if they are semantically close and a negative pair if they are semantically different. Our experiments showed that PNDA improves the performance of contrastive learning.
• Score: 50.21289052547294
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Rotation is frequently listed as a candidate for data augmentation in contrastive learning but seldom provides satisfactory improvements. We argue that this is because the rotated image is always treated as either positive or negative. The semantics of an image can be rotation-invariant or rotation-variant, so whether the rotated image is treated as positive or negative should be determined based on the content of the image. Therefore, we propose a novel augmentation strategy, adaptive Positive or Negative Data Augmentation (PNDA), in which an original and its rotated image are a positive pair if they are semantically close and a negative pair if they are semantically different. To achieve PNDA, we first determine whether rotation is positive or negative on an image-by-image basis in an unsupervised way. Then, we apply PNDA to contrastive learning frameworks. Our experiments showed that PNDA improves the performance of contrastive learning. The code is available at \url{ https://github.com/AtsuMiyai/rethinking_rotation}.

Related papers

• Similarity Contrastive Estimation for Image and Video Soft Contrastive Self-Supervised Learning [0.22940141855172028]
  We propose a novel formulation of contrastive learning using semantic similarity between instances. Our training objective is a soft contrastive one that brings the positives closer and estimates a continuous distribution to push or pull negative instances. We show that SCE reaches state-of-the-art results for pretraining video representation and that the learned representation can generalize to video downstream tasks.
  arXiv  Detail & Related papers  (2022-12-21T16:56:55Z)
• Debiased Contrastive Learning of Unsupervised Sentence Representations [88.58117410398759]
  Contrastive learning is effective in improving pre-trained language models (PLM) to derive high-quality sentence representations. Previous works mostly adopt in-batch negatives or sample from training data at random. We present a new framework textbfDCLR to alleviate the influence of these improper negatives.
  arXiv  Detail & Related papers  (2022-05-02T05:07:43Z)
• Exploring Negatives in Contrastive Learning for Unpaired Image-to-Image Translation [12.754320302262533]
  We introduce a new negative Pruning technology for Unpaired image-to-image Translation (PUT) by sparsifying and ranking the patches. The proposed algorithm is efficient, flexible and enables the model to learn essential information between corresponding patches stably.
  arXiv  Detail & Related papers  (2022-04-23T08:31:18Z)
• Residual Relaxation for Multi-view Representation Learning [64.40142301026805]
  Multi-view methods learn by aligning multiple views of the same image. Some useful augmentations, such as image rotation, are harmful for multi-view methods because they cause a semantic shift. We develop a generic approach, Pretext-aware Residual Relaxation (Prelax), that relaxes the exact alignment.
  arXiv  Detail & Related papers  (2021-10-28T17:57:17Z)
• Inverse Problems Leveraging Pre-trained Contrastive Representations [88.70821497369785]
  We study a new family of inverse problems for recovering representations of corrupted data. We propose a supervised inversion method that uses a contrastive objective to obtain excellent representations for highly corrupted images. Our method outperforms end-to-end baselines even with a fraction of the labeled data in a wide range of forward operators.
  arXiv  Detail & Related papers  (2021-10-14T15:06:30Z)
• Improving Contrastive Learning by Visualizing Feature Transformation [37.548120912055595]
  In this paper, we attempt to devise a feature-level data manipulation, differing from data augmentation, to enhance the generic contrastive self-supervised learning. We first design a visualization scheme for pos/neg score (Pos/neg score indicates similarity of pos/neg pair.) distribution, which enables us to analyze, interpret and understand the learning process. Experiment results show that our proposed Feature Transformation can improve at least 6.0% accuracy on ImageNet-100 over MoCo baseline, and about 2.0% accuracy on ImageNet-1K over the MoCoV2 baseline.
  arXiv  Detail & Related papers  (2021-08-06T07:26:08Z)
• ISD: Self-Supervised Learning by Iterative Similarity Distillation [39.60300771234578]
  We introduce a self supervised learning algorithm where we use a soft similarity for the negative images rather than a binary distinction between positive and negative pairs. Our method achieves better results compared to state-of-the-art models like BYOL and MoCo on transfer learning settings.
  arXiv  Detail & Related papers  (2020-12-16T20:50:17Z)
• Boosting Contrastive Self-Supervised Learning with False Negative Cancellation [40.71224235172881]
  A fundamental problem in contrastive learning is mitigating the effects of false negatives. We propose novel approaches to identify false negatives, as well as two strategies to mitigate their effect. Our method exhibits consistent improvements over existing contrastive learning-based methods.
  arXiv  Detail & Related papers  (2020-11-23T22:17:21Z)
• Contrastive Learning for Unpaired Image-to-Image Translation [64.47477071705866]
  In image-to-image translation, each patch in the output should reflect the content of the corresponding patch in the input, independent of domain. We propose a framework based on contrastive learning to maximize mutual information between the two. We demonstrate that our framework enables one-sided translation in the unpaired image-to-image translation setting, while improving quality and reducing training time.
  arXiv  Detail & Related papers  (2020-07-30T17:59:58Z)
• Whitening for Self-Supervised Representation Learning [129.57407186848917]
  We propose a new loss function for self-supervised representation learning (SSL) based on the whitening of latent-space features. Our solution does not require asymmetric networks and it is conceptually simple.
  arXiv  Detail & Related papers  (2020-07-13T12:33:25Z)

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.