paper-with-me

홈 › Papers

Few-Shot Class-Incremental Learning via Entropy-Regularized Data-Free Replay

2022-07-22 · Huan Liu, Li Gu, Zhixiang Chi, Yang Wang, Yuanhao Yu, Jun Chen, Jin Tang

Few-shot class-incremental learning (FSCIL) has been proposed aiming to enable a deep learning system to incrementally learn new classes with limited data. Recently, a pioneer claims that the commonly used replay-based method in class-incremental learning (CIL) is ineffective and thus not preferred for FSCIL. This has, if truth, a significant influence on the fields of FSCIL. In this paper, we show through empirical results that adopting the data replay is surprisingly favorable. However, storing and replaying old data can lead to a privacy concern. To address this issue, we alternatively propose using data-free replay that can synthesize data by a generator without accessing real data. In observing the the effectiveness of uncertain data for knowledge distillation, we impose entropy regularization in the generator training to encourage more uncertain examples. Moreover, we propose to relabel the generated data with one-hot-like labels. This modification allows the network to learn by solely minimizing the cross-entropy loss, which mitigates the problem of balancing different objectives in the conventional knowledge distillation approach. Finally, we show extensive experimental results and analysis on CIFAR-100, miniImageNet and CUB-200 to demonstrate the effectiveness of our proposed one.

📄 PDF Abstract BibTeX arXiv:2207.11213

Code (1)

liuh127/FSCIL-via-Entropy-regularized-DF-Replay 공식 구현 pytorch

Tasks

class-incremental learningClass Incremental LearningFew-Shot Class-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.…
Entropy Regularization 설명 없음

Similar Papers 제목 키워드 기반

ZEBRA: Zero-Shot Entropy-Regularized Prompt Learning for Base-to-Novel Generalization in Audio-Language Models

2026-06-30 · Asif Hanif, Mohammad Yaqub arxiv

Audio-Language Models (ALMs) achieve strong zero-shot performance by aligning audio with textual class descriptions. Although prompt learning improves accuracy on base classes through few-shot supervised adaptation, we o…

Audio Classification

On the Soft-Subnetwork for Few-shot Class Incremental Learning

2022-09-15 · Haeyong Kang, Jaehong Yoon, Sultan Rizky Hikmawan Madjid, Sung Ju Hwang 외

Inspired by Regularized Lottery Ticket Hypothesis (RLTH), which hypothesizes that there exist smooth (non-binary) subnetworks within a dense network that achieve the competitive performance of the dense network, we propo…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning

Few-shot Class-Incremental Learning via Generative Co-Memory Regularization

2026-01-12 · Kexin Bao, Yong Li, Dan Zeng, Shiming Ge arxiv

Few-shot class-incremental learning (FSCIL) aims to incrementally learn models from a small amount of novel data, which requires strong representation and adaptation ability of models learned under few-example supervisio…

Few-Shot Class-Incremental LearningDomain Adaptation

HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning

2026-04-17 · Eunju Lee, MiHyeon Kim, JuneHyoung Kwon, Yoonji Lee 외 arxiv

Pretrained Vision-Language Models (VLMs) like CLIP show promise in continual learning, but existing Few-Shot Class-Incremental Learning (FSCIL) methods assume homogeneous domains and balanced data distributions, limiting…

Few-Shot Class-Incremental LearningContinual Learning

Towards Robust Few-shot Class Incremental Learning in Audio Classification using Contrastive Representation

2024-07-27 · Riyansha Singh, Parinita Nema, Vinod K Kurmi

In machine learning applications, gradual data ingress is common, especially in audio processing where incremental learning is vital for real-time analytics. Few-shot class-incremental learning addresses challenges arisi…

Audio Classificationclass-incremental learningClass Incremental LearningContrastive Learning+2