paper-with-me

홈 › Papers

Online Class-Incremental Continual Learning with Adversarial Shapley Value

2020-08-31 · Dongsub Shim, Zheda Mai, Jihwan Jeong, Scott Sanner, Hyunwoo Kim, Jongseong Jang

As image-based deep learning becomes pervasive on every device, from cell phones to smart watches, there is a growing need to develop methods that continually learn from data while minimizing memory footprint and power consumption. While memory replay techniques have shown exceptional promise for this task of continual learning, the best method for selecting which buffered images to replay is still an open question. In this paper, we specifically focus on the online class-incremental setting where a model needs to learn new classes continually from an online data stream. To this end, we contribute a novel Adversarial Shapley value scoring method that scores memory data samples according to their ability to preserve latent decision boundaries for previously observed classes (to maintain learning stability and avoid forgetting) while interfering with latent decision boundaries of current classes being learned (to encourage plasticity and optimal learning of new class boundaries). Overall, we observe that our proposed ASER method provides competitive or improved performance compared to state-of-the-art replay-based continual learning methods on a variety of datasets.

📄 PDF Abstract BibTeX arXiv:2009.00093

Code (3)

RaptorMai/online-continual-learning 공식 구현 pytorch
yaqianzhang/repeatedaugmentedrehearsal pytorch
https://gitlab.com/viper-purdue/ocil-real-world-food-image-classification pytorch

Tasks

Continual LearningOpen-Ended Question Answering

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

Shapley Neuron Values for Continual Learning: Which Neurons Matter Most?

2026-05-15 · Mohammad Ali Vahedifar, Abhisek Ray, Qi Zhang arxiv

Continual learning enables neural networks to learn tasks sequentially without forgetting previously acquired knowledge. However, neural networks suffer from catastrophic forgetting, where learning new tasks degrades per…

Class Incremental LearningContinual Learning

ORDisCo: Effective and Efficient Usage of Incremental Unlabeled Data for Semi-supervised Continual Learning

2021-01-02 · CVPR 2021 1 · Liyuan Wang, Kuo Yang, Chongxuan Li, Lanqing Hong 외

Continual learning usually assumes the incoming data are fully labeled, which might not be applicable in real applications. In this work, we consider semi-supervised continual learning (SSCL) that incrementally learns fr…

Continual LearningGenerative Adversarial Network

Susceptibility of Continual Learning Against Adversarial Attacks

2022-07-11 · Hikmat Khan, Pir Masoom Shah, Syed Farhan Alam Zaidi, Saif ul Islam 외

Recent continual learning approaches have primarily focused on mitigating catastrophic forgetting. Nevertheless, two critical areas have remained relatively unexplored: 1) evaluating the robustness of proposed methods an…

class-incremental learningClass Incremental LearningContinual LearningIncremental Learning

Self-Supervised Training Enhances Online Continual Learning

2021-03-25 · Jhair Gallardo, Tyler L. Hayes, Christopher Kanan

In continual learning, a system must incrementally learn from a non-stationary data stream without catastrophic forgetting. Recently, multiple methods have been devised for incrementally learning classes on large-scale i…

Continual Learningimage-classificationImage Classification

Incremental Concept Learning via Online Generative Memory Recall

2019-07-05 · Huaiyu Li, Wei-Ming Dong, Bao-Gang Hu

The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previousl…

class-incremental learningClass Incremental LearningGenerative Adversarial NetworkIncremental Learning