paper-with-me

Papers

Augmentation-aware Self-supervised Learning with Conditioned Projector

2023-05-31 · Marcin Przewięźlikowski, Mateusz Pyla, Bartosz Zieliński, Bartłomiej Twardowski, Jacek Tabor, Marek Śmieja

Self-supervised learning (SSL) is a powerful technique for learning from unlabeled data. By learning to remain invariant to applied data augmentations, methods such as SimCLR and MoCo can reach quality on par with supervised approaches. However, this invariance may be detrimental for solving downstream tasks that depend on traits affected by augmentations used during pretraining, such as color. In this paper, we propose to foster sensitivity to such characteristics in the representation space by modifying the projector network, a common component of self-supervised architectures. Specifically, we supplement the projector with information about augmentations applied to images. For the projector to take advantage of this auxiliary conditioning when solving the SSL task, the feature extractor learns to preserve the augmentation information in its representations. Our approach, coined Conditional Augmentation-aware Self-supervised Learning (CASSLE), is directly applicable to typical joint-embedding SSL methods regardless of their objective functions. Moreover, it does not require major changes in the network architecture or prior knowledge of downstream tasks. In addition to an analysis of sensitivity towards different data augmentations, we conduct a series of experiments, which show that CASSLE improves over various SSL methods, reaching state-of-the-art performance in multiple downstream tasks.

📄 PDF Abstract BibTeX arXiv:2306.06082

Code (1)

gmum/cassle 공식 구현 pytorch

Tasks

Self-Supervised LearningSensitivity

Methods 이 논문이 사용한 방법론

Bitcoin Customer Service Number +1-833-534-1729 설명 없음
Average Pooling 설명 없음
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Residual Connection 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Batch Normalization 설명 없음

Similar Papers 제목 키워드 기반

Toward a Geometrical Understanding of Self-supervised Contrastive Learning

2022-05-13 · Romain Cosentino, Anirvan Sengupta, Salman Avestimehr, Mahdi Soltanolkotabi 외

Self-supervised learning (SSL) is currently one of the premier techniques to create data representations that are actionable for transfer learning in the absence of human annotations. Despite their success, the underlyin…

Contrastive LearningData AugmentationSelf-Supervised LearningTransfer Learning

Self-supervised Representation Learning From Random Data Projectors

2023-10-11 · Yi Sui, Tongzi Wu, Jesse C. Cresswell, Ga Wu 외

Self-supervised representation learning~(SSRL) has advanced considerably by exploiting the transformation invariance assumption under artificially designed data augmentations. While augmentation-based SSRL algorithms pus…

Data AugmentationRepresentation Learning

Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization

2026-07-08 · Adam M. Oberman arxiv

Self-supervised learning matches supervised accuracy from a fraction of the labels, but the labeled-sample efficiency behind this has lacked a theoretical explanation. We provide one. Data augmentation induces a similari…

Self-Supervised LearningData Augmentation

Variance Covariance Regularization Enforces Pairwise Independence in Self-Supervised Representations

2022-09-29 · Grégoire Mialon, Randall Balestriero, Yann Lecun

Self-Supervised Learning (SSL) methods such as VICReg, Barlow Twins or W-MSE avoid collapse of their joint embedding architectures by constraining or regularizing the covariance matrix of their projector's output. This s…

Domain GeneralizationSelf-Supervised Learning

From Canonical Correlation Analysis to Self-supervised Graph Neural Networks

2021-06-23 · NeurIPS 2021 12 · Hengrui Zhang, Qitian Wu, Junchi Yan, David Wipf 외

We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data. It follows the previous methods that generate two views of an input graph through data augmentation. How…

Data AugmentationRepresentation Learning