Sharing the Learned Knowledge-base to Estimate Convolutional Filter Parameters for Continual Image Restoration

2025-11-07 · Aupendu Kar, Krishnendu Ghosh, Prabir Kumar Biswas arxiv

Continual learning is an emerging topic in the field of deep learning, where a model is expected to learn continuously for new upcoming tasks without forgetting previous experiences. This field has witnessed numerous advancements, but few works have been attempted in the direction of image restoration. Handling large image sizes and the divergent nature of various degradation poses a unique challenge in the restoration domain. However, existing works require heavily engineered architectural modifications for new task adaptation, resulting in significant computational overhead. Regularization-based methods are unsuitable for restoration, as different restoration challenges require different kinds of feature processing. In this direction, we propose a simple modification of the convolution layer to adapt the knowledge from previous restoration tasks without touching the main backbone architecture. Therefore, it can be seamlessly applied to any deep architecture without any structural modifications. Unlike other approaches, we demonstrate that our model can increase the number of trainable parameters without significantly increasing computational overhead or inference time. Experimental validation demonstrates that new restoration tasks can be introduced without compromising the performance of existing tasks. We also show that performance on new restoration tasks improves by adapting the knowledge from the knowledge base created by previous restoration tasks. The code is available at https://github.com/aupendu/continual-restore.

📄 PDF Abstract BibTeX arXiv:2511.05421

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning Image Restoration

Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing

2017-12-07 · Syed Shakib Sarwar, Aayush Ankit, Kaushik Roy

Deep convolutional neural network (DCNN) based supervised learning is a widely practiced approach for large-scale image classification. However, retraining these large networks to accommodate new, previously unseen data …

General Classification image-classification Image Classification Incremental Learning+1

Learning $3$D-FilterMap for Deep Convolutional Neural Networks

2018-01-05 · Yingzhen Yang, Jianchao Yang, Ning Xu, Wei Han

We present a novel and compact architecture for deep Convolutional Neural Networks (CNNs) in this paper, termed $3$D-FilterMap Convolutional Neural Networks ($3$D-FM-CNNs). The convolution layer of $3$D-FM-CNN learns a c…

Equivariance Discovery by Learned Parameter-Sharing

2022-04-07 · Raymond A. Yeh, Yuan-Ting Hu, Mark Hasegawa-Johnson, Alexander G. Schwing

Designing equivariance as an inductive bias into deep-nets has been a prominent approach to build effective models, e.g., a convolutional neural network incorporates translation equivariance. However, incorporating these…

Inductive Bias Translation

Implicit Priors for Knowledge Sharing in Bayesian Neural Networks

2019-12-02 · Jack K. Fitzsimons, Sebastian M. Schmon, Stephen J. Roberts

Bayesian interpretations of neural network have a long history, dating back to early work in the 1990's and have recently regained attention because of their desirable properties like uncertainty estimation, model robust…

Transfer Learning

Flexible Multi-task Networks by Learning Parameter Allocation

2019-10-10 · Krzysztof Maziarz, Efi Kokiopoulou, Andrea Gesmundo, Luciano Sbaiz 외

This paper proposes a novel learning method for multi-task applications. Multi-task neural networks can learn to transfer knowledge across different tasks by using parameter sharing. However, sharing parameters between u…

Multi-Task Learning