paper-with-me

Papers

SRIL: Selective Regularization for Class-Incremental Learning

2023-05-09 · Jisu Han, Jaemin Na, Wonjun Hwang

Human intelligence gradually accepts new information and accumulates knowledge throughout the lifespan. However, deep learning models suffer from a catastrophic forgetting phenomenon, where they forget previous knowledge when acquiring new information. Class-Incremental Learning aims to create an integrated model that balances plasticity and stability to overcome this challenge. In this paper, we propose a selective regularization method that accepts new knowledge while maintaining previous knowledge. We first introduce an asymmetric feature distillation method for old and new classes inspired by cognitive science, using the gradient of classification and knowledge distillation losses to determine whether to perform pattern completion or pattern separation. We also propose a method to selectively interpolate the weight of the previous model for a balance between stability and plasticity, and we adjust whether to transfer through model confidence to ensure the performance of the previous class and enable exploratory learning. We validate the effectiveness of the proposed method, which surpasses the performance of existing methods through extensive experimental protocols using CIFAR-100, ImageNet-Subset, and ImageNet-Full.

📄 PDF Abstract BibTeX arXiv:2305.05175

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learningClass Incremental LearningIncremental LearningKnowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

Dual-Selective Network for Domain-Incremental Change Detection

2026-07-02 · Yuzhi He, Junxi Huang, Haorui Wu, Jiahui Qu arxiv

Domain-incremental change detection (DICD) continuously adapts models to new geographic domains while preserving prior knowledge. However, a structural mismatch exists: the label space remains fixed while domain characte…

Computational EfficiencyChange Detection

Spectral-Aware Analytic Class-Incremental Learning for Long-Tailed Distributions

2026-07-24 · Quyen Tran, Hai Nguyen, Quan Dao, Zhuowei Li 외 arxiv

Analytic Continual Learning (ACL) offers a computationally efficient alternative to gradient-based approaches. Recent ACL methods are based on Recursive Least Squares (RLS) and have achieved the state-of-the-art results …

class-incremental learningComputational EfficiencyContinual Learning

CLSRIL-23: Cross Lingual Speech Representations for Indic Languages

2021-07-15 · Anirudh Gupta, Harveen Singh Chadha, Priyanshi Shah, Neeraj Chhimwal 외

We present a CLSRIL-23, a self supervised learning based audio pre-trained model which learns cross lingual speech representations from raw audio across 23 Indic languages. It is built on top of wav2vec 2.0 which is solv…

Self-Supervised Learningspeech-recognitionSpeech Recognition

More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning

2020-08-01 · ECCV 2020 8 · Yu Liu, Sarah Parisot, Gregory Slabaugh, Xu Jia 외

Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning","Overcoming catastrophic forgetting in neural networks is a long-standing and core research objective for incremental learning. Notable studi…

Incremental Learning

Selective Output Smoothing Regularization: Regularize Neural Networks by Softening Output Distributions

2021-03-29 · Xuan Cheng, Tianshu Xie, Xiaomin Wang, Qifeng Weng 외

In this paper, we propose Selective Output Smoothing Regularization, a novel regularization method for training the Convolutional Neural Networks (CNNs). Inspired by the diverse effects on training from different samples…

image-classificationImage Classification