Learnable Expansion-and-Compression Network for Few-shot Class-Incremental Learning

2021-04-06 · Boyu Yang, Mingbao Lin, Binghao Liu, Mengying Fu, Chang Liu, Rongrong Ji, Qixiang Ye

Few-shot class-incremental learning (FSCIL), which targets at continuously expanding model's representation capacity under few supervisions, is an important yet challenging problem. On the one hand, when fitting new tasks (novel classes), features trained on old tasks (old classes) could significantly drift, causing catastrophic forgetting. On the other hand, training the large amount of model parameters with few-shot novel-class examples leads to model over-fitting. In this paper, we propose a learnable expansion-and-compression network (LEC-Net), with the aim to simultaneously solve catastrophic forgetting and model over-fitting problems in a unified framework. By tentatively expanding network nodes, LEC-Net enlarges the representation capacity of features, alleviating feature drift of old network from the perspective of model regularization. By compressing the expanded network nodes, LEC-Net purses minimal increase of model parameters, alleviating over-fitting of the expanded network from a perspective of compact representation. Experiments on the CUB/CIFAR-100 datasets show that LEC-Net improves the baseline by 5~7% while outperforms the state-of-the-art by 5~6%. LEC-Net also demonstrates the potential to be a general incremental learning approach with dynamic model expansion capability.

📄 PDF Abstract BibTeX arXiv:2104.02281

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning

Feature Expansion and enhanced Compression for Class Incremental Learning

2024-05-13 · Quentin Ferdinand, Gilles Le Chenadec, Benoit Clement, Panagiotis Papadakis 외

Class incremental learning consists in training discriminative models to classify an increasing number of classes over time. However, doing so using only the newly added class data leads to the known problem of catastrop…

class-incremental learning Class Incremental Learning Data Augmentation Incremental Learning

Ambiguity-Guided Learnable Distribution Calibration for Semi-Supervised Few-Shot Class-Incremental Learning

2025-07-31 · Fan Lyu, Linglan Zhao, Chengyan Liu, Yinying Mei 외 arxiv

Few-Shot Class-Incremental Learning (FSCIL) focuses on models learning new concepts from limited data while retaining knowledge of previous classes. Recently, many studies have started to leverage unlabeled samples to as…

Few-Shot Class-Incremental Learning

Learnable Distribution Calibration for Few-Shot Class-Incremental Learning

2022-10-01 · Binghao Liu, Boyu Yang, Lingxi Xie, Ren Wang 외

Few-shot class-incremental learning (FSCIL) faces challenges of memorizing old class distributions and estimating new class distributions given few training samples. In this study, we propose a learnable distribution cal…

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Few-Shot Learning+2

Class-Incremental Exemplar Compression for Class-Incremental Learning

2023-03-24 · CVPR 2023 1 · Zilin Luo, Yaoyao Liu, Bernt Schiele, Qianru Sun

Exemplar-based class-incremental learning (CIL) finetunes the model with all samples of new classes but few-shot exemplars of old classes in each incremental phase, where the "few-shot" abides by the limited memory budge…

Bilevel Optimization class-incremental learning Class Incremental Learning Incremental Learning

Unlocking Prototype Potential: An Efficient Tuning Framework for Few-Shot Class-Incremental Learning

2026-02-05 · Shengqin Jiang, Xiaoran Feng, Yuankai Qi, Haokui Zhang 외 arxiv

Few-shot class-incremental learning (FSCIL) seeks to continuously learn new classes from very limited samples while preserving previously acquired knowledge. Traditional methods often utilize a frozen pre-trained feature…