paper-with-me

홈 › Papers

UER: A Heuristic Bias Addressing Approach for Online Continual Learning

2023-09-08 · Huiwei Lin, Shanshan Feng, Baoquan Zhang, Hongliang Qiao, Xutao Li, Yunming Ye

Online continual learning aims to continuously train neural networks from a continuous data stream with a single pass-through data. As the most effective approach, the rehearsal-based methods replay part of previous data. Commonly used predictors in existing methods tend to generate biased dot-product logits that prefer to the classes of current data, which is known as a bias issue and a phenomenon of forgetting. Many approaches have been proposed to overcome the forgetting problem by correcting the bias; however, they still need to be improved in online fashion. In this paper, we try to address the bias issue by a more straightforward and more efficient method. By decomposing the dot-product logits into an angle factor and a norm factor, we empirically find that the bias problem mainly occurs in the angle factor, which can be used to learn novel knowledge as cosine logits. On the contrary, the norm factor abandoned by existing methods helps remember historical knowledge. Based on this observation, we intuitively propose to leverage the norm factor to balance the new and old knowledge for addressing the bias. To this end, we develop a heuristic approach called unbias experience replay (UER). UER learns current samples only by the angle factor and further replays previous samples by both the norm and angle factors. Extensive experiments on three datasets show that UER achieves superior performance over various state-of-the-art methods. The code is in https://github.com/FelixHuiweiLin/UER.

📄 PDF Abstract BibTeX arXiv:2309.04081

Code (0)

등록된 구현이 없습니다.

Tasks

Continual Learning

Methods 이 논문이 사용한 방법론

Experience Replay Experience Replay is a replay memory technique used in reinforcement learning where we store the agent’s experiences at each time-step, $e\_{t} = \left(s\_{t}, a\_{t}, r\_{t},…

Similar Papers 제목 키워드 기반

CBA: Improving Online Continual Learning via Continual Bias Adaptor

2023-08-14 · ICCV 2023 1 · Quanziang Wang, Renzhen Wang, Yichen Wu, Xixi Jia 외

Online continual learning (CL) aims to learn new knowledge and consolidate previously learned knowledge from non-stationary data streams. Due to the time-varying training setting, the model learned from a changing distri…

Continual Learning

Dual-CBA: Improving Online Continual Learning via Dual Continual Bias Adaptors from a Bi-level Optimization Perspective

2024-08-26 · Quanziang Wang, Renzhen Wang, Yichen Wu, Xixi Jia 외

In online continual learning (CL), models trained on changing distributions easily forget previously learned knowledge and bias toward newly received tasks. To address this issue, we present Continual Bias Adaptor (CBA),…

Continual Learning

Adaptive Shortcut Debiasing for Online Continual Learning

2023-12-14 · Doyoung Kim, Dongmin Park, Yooju Shin, Jihwan Bang 외

We propose a novel framework DropTop that suppresses the shortcut bias in online continual learning (OCL) while being adaptive to the varying degree of the shortcut bias incurred by continuously changing environment. By …

Continual Learning

Continual Normalization: Rethinking Batch Normalization for Online Continual Learning

2022-03-30 · ICLR 2022 4 · Quang Pham, Chenghao Liu, Steven Hoi

Existing continual learning methods use Batch Normalization (BN) to facilitate training and improve generalization across tasks. However, the non-i.i.d and non-stationary nature of continual learning data, especially in …

Continual Learning

Online Analytic Exemplar-Free Continual Learning with Large Models for Imbalanced Autonomous Driving Task

2024-05-28 · Huiping Zhuang, Di Fang, Kai Tong, Yuchen Liu 외

In autonomous driving, even a meticulously trained model can encounter failures when facing unfamiliar scenarios. One of these scenarios can be formulated as an online continual learning (OCL) problem. That is, data come…

Autonomous DrivingContinual LearningExemplar-Free