Enhanced Few-Shot Class-Incremental Learning via Ensemble Models

2024-01-14 · Mingli Zhu, Zihao Zhu, Sihong Chen, Chen Chen, Baoyuan Wu

Few-shot class-incremental learning (FSCIL) aims to continually fit new classes with limited training data, while maintaining the performance of previously learned classes. The main challenges are overfitting the rare new training samples and forgetting old classes. While catastrophic forgetting has been extensively studied, the overfitting problem has attracted less attention in FSCIL. To tackle overfitting challenge, we design a new ensemble model framework cooperated with data augmentation to boost generalization. In this way, the enhanced model works as a library storing abundant features to guarantee fast adaptation to downstream tasks. Specifically, the multi-input multi-output ensemble structure is applied with a spatial-aware data augmentation strategy, aiming at diversifying the feature extractor and alleviating overfitting in incremental sessions. Moreover, self-supervised learning is also integrated to further improve the model generalization. Comprehensive experimental results show that the proposed method can indeed mitigate the overfitting problem in FSCIL, and outperform the state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2401.07208

Code (0)

등록된 구현이 없습니다.

Tasks

class-incremental learning Class Incremental Learning Data Augmentation Few-Shot Class-Incremental Learning Incremental Learning Self-Supervised Learning

Methods 이 논문이 사용한 방법론

Library 설명 없음

TLCE: Transfer-Learning Based Classifier Ensembles for Few-Shot Class-Incremental Learning

2023-12-07 · Shuangmei Wang, Yang Cao, Tieru Wu

Few-shot class-incremental learning (FSCIL) struggles to incrementally recognize novel classes from few examples without catastrophic forgetting of old classes or overfitting to new classes. We propose TLCE, which ensemb…

class-incremental learning Class Incremental Learning Few-Shot Class-Incremental Learning Incremental Learning+1

Tripartite Weight-Space Ensemble for Few-Shot Class-Incremental Learning

2025-01-01 · CVPR 2025 1 · JunTae Lee, Munawar Hayat, Sungrack Yun

Few-shot class incremental learning (FSCIL) enables the continual learning of new concepts with only a few training examples. In FSCIL, the model undergoes substantial updates, making it prone to forgetting previous …

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

PKI: Prior Knowledge-Infused Neural Network for Few-Shot Class-Incremental Learning

2026-01-13 · Kexin Baoa, Fanzhao Lin, Zichen Wang, Yong Li 외 arxiv

Few-shot class-incremental learning (FSCIL) aims to continually adapt a model on a limited number of new-class examples, facing two well-known challenges: catastrophic forgetting and overfitting to new classes. Existing …

Few-Shot Class-Incremental Learning

Reference Twice: A Simple and Unified Baseline for Few-Shot Instance Segmentation

2023-01-03 · Yue Han, Jiangning Zhang, Yabiao Wang, Chengjie Wang 외

Few-Shot Instance Segmentation (FSIS) requires detecting and segmenting novel classes with limited support examples. Existing methods based on Region Proposal Networks (RPNs) face two issues: 1) Overfitting suppresses no…

Benchmarking Few-shot Instance Segmentation Few-Shot Object Detection Instance Segmentation+5

Memorizing Complementation Network for Few-Shot Class-Incremental Learning

2022-08-11 · Zhong Ji, Zhishen Hou, Xiyao Liu, Yanwei Pang 외

Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems. The inaccessibility of old cla…

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