English
Related papers

Related papers: Not All Forgetting Is Equal: Architecture-Dependen…

200 papers

We hypothesize that disentangled feature representations suffer less from catastrophic forgetting. As a case study we perform explicit disentanglement of color and shape, by adjusting the network architecture. We tested classification…

Computer Vision and Pattern Recognition · Computer Science 2020-07-14 David Berga , Marc Masana , Joost Van de Weijer

Federated learning is an emerging research paradigm enabling collaborative training of machine learning models among different organizations while keeping data private at each institution. Despite recent progress, there remain fundamental…

Machine Learning · Computer Science 2022-04-15 Liangqiong Qu , Yuyin Zhou , Paul Pu Liang , Yingda Xia , Feifei Wang , Ehsan Adeli , Li Fei-Fei , Daniel Rubin

Continual Semantic Segmentation (CSS) seeks to incrementally learn to segment novel classes while preserving knowledge of previously encountered ones. Recent advancements in CSS have been largely driven by the adoption of Pre-trained Vision…

Computer Vision and Pattern Recognition · Computer Science 2025-08-07 Duzhen Zhang , Yong Ren , Wei Cong , Junhao Zheng , Qiaoyi Su , Shuncheng Jia , Zhong-Zhi Li , Xuanle Zhao , Ye Bai , Feilong Chen , Qi Tian , Tielin Zhang

We identify a phenomenon, which we refer to as multi-model forgetting, that occurs when sequentially training multiple deep networks with partially-shared parameters; the performance of previously-trained models degrades as one optimizes a…

Deep neural networks are used in many state-of-the-art systems for machine perception. Once a network is trained to do a specific task, e.g., bird classification, it cannot easily be trained to do new tasks, e.g., incrementally learning to…

Artificial Intelligence · Computer Science 2017-11-10 Ronald Kemker , Marc McClure , Angelina Abitino , Tyler Hayes , Christopher Kanan

Neural networks suffer from catastrophic forgetting in class-incremental learning (CIL) settings. Rehearsal$\unicode{x2013}$replaying a subset of past samples$\unicode{x2013}$is a well-established mitigation strategy. However, recent…

Machine Learning · Computer Science 2026-05-15 Alberto Tamajo , Srinandan Dasmahapatra , Rahman Attar

A discriminatively trained neural net classifier can fit the training data perfectly if all information about its input other than class membership has been discarded prior to the output layer. Surprisingly, past research has discovered…

Machine Learning · Computer Science 2021-07-23 Piotr Teterwak , Chiyuan Zhang , Dilip Krishnan , Michael C. Mozer

Transfer learning followed by fine-tuning is widely adopted in medical image classification due to consistent gains in diagnostic performance. However, in multi-class settings with overlapping visual features, improvements in accuracy do…

Computer Vision and Pattern Recognition · Computer Science 2026-04-10 Kabilan Elangovan , Daniel Ting

Deep neural networks are over-parameterized and easily overfit the datasets they train on. In the extreme case, it has been shown that these networks can memorize a training set with fully randomized labels. We propose using the curvature…

Machine Learning · Computer Science 2023-10-03 Isha Garg , Deepak Ravikumar , Kaushik Roy

In the context of medical imaging and machine learning, one of the most pressing challenges is the effective adaptation of pre-trained models to specialized medical contexts. Despite the availability of advanced pre-trained models, their…

Computer Vision and Pattern Recognition · Computer Science 2024-06-17 Ana Davila , Jacinto Colan , Yasuhisa Hasegawa

Motivated by the desire to exploit patterns shared across classes, we present a simple yet effective class-specific memory module for fine-grained feature learning. The memory module stores the prototypical feature representation for each…

Computer Vision and Pattern Recognition · Computer Science 2020-12-15 Weijian Deng , Joshua Marsh , Stephen Gould , Liang Zheng

Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required replaying stored exemplars from prior tasks, which is often impractical. By contrast,…

Machine Learning · Computer Science 2026-05-26 Martin Marek , Dongkyu Cho , Shikai Qiu , Rumi Chunara , Pavel Izmailov , Andrew Gordon Wilson

Adaptive batch size methods aim to accelerate neural network training, but existing approaches apply identical adaptation strategies across all architectures, assuming a one-size-fits-all solution. We introduce DEBA (Dynamic Efficient Batch…

Machine Learning · Computer Science 2025-11-07 François Belias , Naser Ezzati-Jivan , Foutse Khomh

Deep neural networks suffer from catastrophic forgetting when continually learning new concepts. In this paper, we analyze this problem from a data imbalance point of view. We argue that the imbalance between old task and new task data…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Leyuan Wang , Liuyu Xiang , Yunlong Wang , Huijia Wu , Zhaofeng He

Recently, self-supervised representation learning gives further development in multimedia technology. Most existing self-supervised learning methods are applicable to packaged data. However, when it comes to streamed data, they are…

Computer Vision and Pattern Recognition · Computer Science 2022-11-03 Zhiwei Lin , Yongtao Wang , Hongxiang Lin

Shortcut learning, where machine learning models exploit spurious correlations in data instead of capturing meaningful features, poses a significant challenge to building robust and generalizable models. This phenomenon is prevalent across…

Machine Learning · Computer Science 2025-09-03 Pirzada Suhail , Vrinda Goel , Amit Sethi

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of…

Machine Learning · Computer Science 2021-06-22 Aditya Golatkar , Alessandro Achille , Avinash Ravichandran , Marzia Polito , Stefano Soatto

Machine unlearning seeks to remove the influence of particular data or class from trained models to meet privacy, legal, or ethical requirements. Existing unlearning methods tend to forget shallowly: phenomenon of an unlearned model pretend…

Machine Learning · Computer Science 2025-07-23 Jaeheun Jung , Bosung Jung , Suhyun Bae , Donghun Lee

A well-trained Convolutional Neural Network can easily be pruned without significant loss of performance. This is because of unnecessary overlap in the features captured by the network's filters. Innovations in network architecture such as…

Computer Vision and Pattern Recognition · Computer Science 2019-02-26 Aaditya Prakash , James Storer , Dinei Florencio , Cha Zhang

Continual learning is the process of training machine learning models on a sequence of tasks where data distributions change over time. A well-known obstacle in this setting is catastrophic forgetting, a phenomenon in which a model…

Machine Learning · Computer Science 2025-02-18 Andrii Krutsylo