{"title":"Pseudo initialization based Few-Shot Class Incremental Learning","authors":"Mingwen Shao , Xinkai Zhuang , Lixu Zhang , Wangmeng Zuo","doi":"10.1016/j.cviu.2024.104067","DOIUrl":null,"url":null,"abstract":"<div><p>Few-Shot Class Incremental Learning (FSCIL) aims to recognize sequentially arriving new classes without catastrophic forgetting old classes. The incremental new classes only contain very few labeled examples for updating the model, which causes overfitting problem. Current popular reserving embedding space method Forward Compatible Training preserves feature space for novel classes. Base class is pushed away from the most similar virtual class, preparing for the incoming novel classes. However, this can lead to pushing the base class to other similar virtual classes. In this paper, we propose a novel FSCIL method in order to overcome the aforementioned problem. Specifically, our core idea is pushing base classes away from the most similar top-K virtual classes to reserve feature space and provide pseudo initialization for the incoming novel classes. To further encourage learning new classes without forgetting, an additional regularization is applied to limit the extent of model updating. Extensive experiments are conducted on CUB200, CIFAR100 and mini-ImageNet, illustrating the performance of our proposed method. The results show that our method outperforms the state-of-the-art method and achieves significant improvement.</p></div>","PeriodicalId":50633,"journal":{"name":"Computer Vision and Image Understanding","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-06-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Computer Vision and Image Understanding","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1077314224001486","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}
引用次数: 0
Abstract
Few-Shot Class Incremental Learning (FSCIL) aims to recognize sequentially arriving new classes without catastrophic forgetting old classes. The incremental new classes only contain very few labeled examples for updating the model, which causes overfitting problem. Current popular reserving embedding space method Forward Compatible Training preserves feature space for novel classes. Base class is pushed away from the most similar virtual class, preparing for the incoming novel classes. However, this can lead to pushing the base class to other similar virtual classes. In this paper, we propose a novel FSCIL method in order to overcome the aforementioned problem. Specifically, our core idea is pushing base classes away from the most similar top-K virtual classes to reserve feature space and provide pseudo initialization for the incoming novel classes. To further encourage learning new classes without forgetting, an additional regularization is applied to limit the extent of model updating. Extensive experiments are conducted on CUB200, CIFAR100 and mini-ImageNet, illustrating the performance of our proposed method. The results show that our method outperforms the state-of-the-art method and achieves significant improvement.
期刊介绍:
The central focus of this journal is the computer analysis of pictorial information. Computer Vision and Image Understanding publishes papers covering all aspects of image analysis from the low-level, iconic processes of early vision to the high-level, symbolic processes of recognition and interpretation. A wide range of topics in the image understanding area is covered, including papers offering insights that differ from predominant views.
Research Areas Include:
• Theory
• Early vision
• Data structures and representations
• Shape
• Range
• Motion
• Matching and recognition
• Architecture and languages
• Vision systems