% IMPORTANT: The following is UTF-8 encoded. This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.
@INPROCEEDINGS{Wang:1037214,
author = {Wang, Qin and Krajsek, Kai and Scharr, Hanno},
title = {{E}quivariant {R}epresentation {L}earning for
{A}ugmentation-based {S}elf-{S}upervised {L}earning via
{I}mage {R}econstruction},
reportid = {FZJ-2025-00547},
pages = {12},
year = {2024},
abstract = {Augmentation-based self-supervised learning methods have
shown remarkable success in self-supervised visual
representation learning, excelling in learning invariant
features but often neglecting equivariant ones. This
limitation reduces the generalizability of foundation
models, particularly for downstream tasks requiring
equivariance. We propose integrating an image reconstruction
task as an auxiliary component in augmentation-based
self-supervised learning algorithms to facilitate
equivariant feature learning without additional parameters.
Our method implements a cross-attention mechanism to blend
features learned from two augmented views, subsequently
reconstructing one of them. This approach is adaptable to
various datasets and augmented-pair based learning methods.
We evaluate its effectiveness on learning equivariant
features through multiple linear regression tasks and
downstream applications on both artificial (3DIEBench) and
natural (ImageNet) datasets. Results consistently
demonstrate significant improvements over standard
augmentation-based self-supervised learning methods and
state-of-the-art approaches, particularly excelling in
scenarios involving combined augmentations. Our method
enhances the learning of both invariant and equivariant
features, leading to more robust and generalizable visual
representations for computer vision tasks.},
month = {Dec},
date = {2024-12-10},
organization = {The Thirty-Eighth Annual Conference on
Neural Information Processing Systems
Workshop: Self-Supervised Learning -
Theory and Practice, Vancouver
(Canada), 10 Dec 2024 - 15 Dec 2024},
cin = {IAS-8 / JSC},
cid = {I:(DE-Juel1)IAS-8-20210421 / I:(DE-Juel1)JSC-20090406},
pnm = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
(SDLs) and Research Groups (POF4-511) / 5112 - Cross-Domain
Algorithms, Tools, Methods Labs (ATMLs) and Research Groups
(POF4-511) / SLNS - SimLab Neuroscience (Helmholtz-SLNS)},
pid = {G:(DE-HGF)POF4-5111 / G:(DE-HGF)POF4-5112 /
G:(DE-Juel1)Helmholtz-SLNS},
typ = {PUB:(DE-HGF)8},
doi = {10.34734/FZJ-2025-00547},
url = {https://juser.fz-juelich.de/record/1037214},
}