Memorizing Complementation Network for Few-Shot Class-Incremental Learning

Zhong Ji

doi:10.1109/TIP.2023.3236160

Memorizing Complementation Network for Few-Shot Class-Incremental Learning

2023-01-01

20

OA

AI

DOI：10.1109/TIP.2023.3236160

Original

Original request for help

Save

Abstract

En 中文

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 classes and the scarcity of the novel samples make it formidable to realize the trade-off between retaining old knowledge and learning novel concepts. Inspired by that different models memorize different knowledge when learning novel concepts, we propose a Memorizing Complementation Network (MCNet) to ensemble multiple models that complements the different memorized knowledge with each other in novel tasks. Additionally, to update the model with few novel samples, we develop a Prototype Smoothing Hard-mining Triplet (PSHT) loss to push the novel samples away from not only each other in current task but also the old distribution. Extensive experiments on three benchmark datasets, e.g., CIFAR100, miniImageNet and CUB200, have demonstrated the superiority of our proposed method.

Keywords:

Task analysis

Power capacitors

Ensemble learning

Knowledge engineering

Feature extraction

Adaptation models

Training

Few-shot learning

class-incremental learning

ensemble learning

memorizing complementation

Memorizing Complementation Network for Few-Shot Class-Incremental Learning

Abstract

Journal

Organization