paper-with-me

Papers

Equivariant Self-Supervised Learning: Encouraging Equivariance in Representations

2021-09-29 · ICLR 2022 4 · Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljacic

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, the property of invariance is a trivial instance of a broader class called equivariance, which can be intuitively understood as the property that representations transform according to the way the inputs transform. Here, we show that rather than using only invariance, pre-training that encourages non-trivial equivariance to some transformations, while maintaining invariance to other transformations, can be used to improve the semantic quality of representations. Specifically, we extend popular SSL methods to a more general fremework which we name Equivariant Self-Supervised Learning (E-SSL). In E-SSL, a simple additional pre-training objective encourages equivariance by predicting the transformations applied to the input. We demonstrate E-SSL’s effectiveness empirically on several popular computer vision benchmarks. Furthermore, we demonstrate usefulness of E-SSL for applications beyond computer vision; in particular, we show its utility on regression problems in photonics science.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Self-Supervised Learning

Similar Papers 제목 키워드 기반

Equivariant Contrastive Learning

2021-10-28 · Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han 외

In state-of-the-art self-supervised learning (SSL) pre-training produces semantically good representations by encouraging them to be invariant under meaningful transformations prescribed from human knowledge. In fact, th…

Contrastive LearningSelf-Supervised Learning

Equivariant Representation Learning via Class-Pose Decomposition

2022-07-07 · Giovanni Luca Marchetti, Gustaf Tegnér, Anastasiia Varava, Danica Kragic

We introduce a general method for learning representations that are equivariant to symmetries of data. Our central idea is to decompose the latent space into an invariant factor and the symmetry group itself. The compone…

Representation Learning

Self-Supervised Learning based on Transformed Image Reconstruction for Equivariance-Coherent Feature Representation

2025-03-24 · Qin Wang, Benjamin Bruns, Hanno Scharr, Kai Krajsek

The equivariant behaviour of features is essential in many computer vision tasks, yet popular self-supervised learning (SSL) methods tend to constrain equivariance by design. We propose a self-supervised learning approac…

Image ReconstructionSelf-Supervised Learning

Self-Supervised Learning for Group Equivariant Neural Networks

2023-03-08 · Yusuke Mukuta, Tatsuya Harada

This paper proposes a method to construct pretext tasks for self-supervised learning on group equivariant neural networks. Group equivariant neural networks are the models whose structure is restricted to commute with th…

Self-Supervised Learning

Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning

2023-06-24 · Sharut Gupta, Joshua Robinson, Derek Lim, Soledad Villar 외

Self-supervised learning converts raw perceptual data such as images to a compact space where simple Euclidean distances measure meaningful variations in data. In this paper, we extend this formulation by adding addition…

Contrastive LearningSelf-Supervised Learning