Paper Detail

Equivariant Experience Replay for Continual Learning in Imaging Inverse Problems

Guixian Xu, Jin Zhu, Jinglai Li, Junqi Tang

arxiv Score 10.0

Published 2026-10-21 · First seen 2026-10-23

Research Track A

Abstract

In this work, we propose Equivariant Experience Replay, a new paradigm for achieving continual learning of deep networks for solving ill-posed imaging inverse problems. Inspired by recent advances on unsupervised learning methods such as equivariant imaging/splitting, we find the exploitation of group-symmetry structure is particularly relevant and effective in continual learning setting for ill-posed inversion tasks. We therefore propose this new experience replay scheme, which is tailored for such inverse problems. Our numerical study demonstrates the superiority of our method compared to existing continual learning methods for inverse problems in medical imaging and image processing.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{xu2026equivariant,
  title = {Equivariant Experience Replay for Continual Learning in Imaging Inverse Problems},
  author = {Guixian Xu and Jin Zhu and Jinglai Li and Junqi Tang},
  year = {2026},
  abstract = {In this work, we propose Equivariant Experience Replay, a new paradigm for achieving continual learning of deep networks for solving ill-posed imaging inverse problems. Inspired by recent advances on unsupervised learning methods such as equivariant imaging/splitting, we find the exploitation of group-symmetry structure is particularly relevant and effective in continual learning setting for ill-posed inversion tasks. We therefore propose this new experience replay scheme, which is tailored for },
  url = {https://arxiv.org/abs/2610.30460},
  keywords = {eess.IV},
  eprint = {2610.30460},
  archiveprefix = {arXiv},
}

Metadata

{}