paper-with-me

Papers

ViewMix: Augmentation for Robust Representation in Self-Supervised Learning

2023-09-06 · Arjon Das, Xin Zhong

Joint Embedding Architecture-based self-supervised learning methods have attributed the composition of data augmentations as a crucial factor for their strong representation learning capabilities. While regional dropout strategies have proven to guide models to focus on lesser indicative parts of the objects in supervised methods, it hasn't been adopted by self-supervised methods for generating positive pairs. This is because the regional dropout methods are not suitable for the input sampling process of the self-supervised methodology. Whereas dropping informative pixels from the positive pairs can result in inefficient training, replacing patches of a specific object with a different one can steer the model from maximizing the agreement between different positive pairs. Moreover, joint embedding representation learning methods have not made robustness their primary training outcome. To this end, we propose the ViewMix augmentation policy, specially designed for self-supervised learning, upon generating different views of the same image, patches are cut and pasted from one view to another. By leveraging the different views created by this augmentation strategy, multiple joint embedding-based self-supervised methodologies obtained better localization capability and consistently outperformed their corresponding baseline methods. It is also demonstrated that incorporating ViewMix augmentation policy promotes robustness of the representations in the state-of-the-art methods. Furthermore, our experimentation and analysis of compute times suggest that ViewMix augmentation doesn't introduce any additional overhead compared to other counterparts.

📄 PDF Abstract BibTeX arXiv:2309.03360

Code (0)

등록된 구현이 없습니다.

Tasks

Representation LearningSelf-Supervised Learning

Methods 이 논문이 사용한 방법론

Focus 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Similar Papers 제목 키워드 기반

Multi-Augmentation for Efficient Visual Representation Learning for Self-supervised Pre-training

2022-05-24 · Van-Nhiem Tran, Chi-En Huang, Shen-Hsuan Liu, Kai-Lin Yang 외

In recent years, self-supervised learning has been studied to deal with the limitation of available labeled-dataset. Among the major components of self-supervised learning, the data augmentation pipeline is one key facto…

Data AugmentationRepresentation LearningSelf-Supervised Learning

SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning

2020-09-16 · CVPR 2021 1 · Colorado J Reed, Sean Metzger, Aravind Srinivas, Trevor Darrell 외

A common practice in unsupervised representation learning is to use labeled data to evaluate the quality of the learned representations. This supervised evaluation is then used to guide critical aspects of the training p…

Data AugmentationRepresentation LearningSelf-Supervised Learning

Homomorphic Self-Supervised Learning

2022-11-15 · T. Anderson Keller, Xavier Suau, Luca Zappella

In this work, we observe that many existing self-supervised learning algorithms can be both unified and generalized when seen through the lens of equivariant representations. Specifically, we introduce a general framewor…

Self-Supervised Learning

Improving Transferability of Representations via Augmentation-Aware Self-Supervision

2021-11-18 · NeurIPS 2021 12 · Hankook Lee, Kibok Lee, Kimin Lee, Honglak Lee 외

Recent unsupervised representation learning methods have shown to be effective in a range of vision tasks by learning representations invariant to data augmentations such as random cropping and color jittering. However, …

Representation LearningTransfer Learning

Random Field Augmentations for Self-Supervised Representation Learning

2023-11-07 · Philip Andrew Mansfield, Arash Afkanpour, Warren Richard Morningstar, Karan Singhal

Self-supervised representation learning is heavily dependent on data augmentations to specify the invariances encoded in representations. Previous work has shown that applying diverse data augmentations is crucial to dow…

Representation Learning