Research map / Continual learning / Online and replay-based
A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks
Xiaoxuan Gong, Jie Ma
Read the paperCheck your idea against 137,217 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes a minimalistic unified framework that lets an image restoration model incrementally learn new restoration tasks without forgetting earlier ones (task-incremental learning for low-level vision).
Problem
Existing all-in-one image restoration methods improve performance over a fixed, limited set of tasks; they do not address how to add new restoration capabilities incrementally to an existing model without catastrophic forgetting.
Approach
Frames image restoration as task-incremental learning, where new restoration tasks are added on top of an existing unified model with a minimalistic design; the abstract provides limited detail beyond this framing.
Closest papers by meaning
- Debiased All-in-one Image Restoration with Task Uncertainty Regularization (AAAI 2025 · similarity 0.90)
- Learning from History: Task-agnostic Model Contrastive Learning for Image Restoration (AAAI 2024 · similarity 0.90)
- Boosting Image Restoration via Priors from Pre-trained Models (CVPR 2024 · similarity 0.88)
- Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts (NeurIPS 2024 · similarity 0.87)
- Complexity Experts are Task-Discriminative Learners for Any Image Restoration (CVPR 2025 · similarity 0.87)
- Controlling Vision-Language Models for Multi-Task Image Restoration (ICLR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
