paper-with-me

Papers

Few-Shot Incremental Learning with Continually Evolved Classifiers

2021-04-07 · CVPR 2021 1 · Chi Zhang, Nan Song, Guosheng Lin, Yun Zheng, Pan Pan, Yinghui Xu

Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points, without forgetting knowledge of old classes. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. Moreover, as training data come in sequence in FSCIL, the learned classifier can only provide discriminative information in individual sessions, while FSCIL requires all classes to be involved for evaluation. In this paper, we address the FSCIL problem from two aspects. First, we adopt a simple but effective decoupled learning strategy of representations and classifiers that only the classifiers are updated in each incremental session, which avoids knowledge forgetting in the representations. By doing so, we demonstrate that a pre-trained backbone plus a non-parametric class mean classifier can beat state-of-the-art methods. Second, to make the classifiers learned on individual sessions applicable to all classes, we propose a Continually Evolved Classifier (CEC) that employs a graph model to propagate context information between classifiers for adaptation. To enable the learning of CEC, we design a pseudo incremental learning paradigm that episodically constructs a pseudo incremental learning task to optimize the graph parameters by sampling data from the base dataset. Experiments on three popular benchmark datasets, including CIFAR100, miniImageNet, and Caltech-USCD Birds-200-2011 (CUB200), show that our method significantly outperforms the baselines and sets new state-of-the-art results with remarkable advantages.

📄 PDF Abstract BibTeX arXiv:2104.03047

Code (1)

icoz69/cec-cvpr2021 pytorch

Tasks

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

Similar Papers 제목 키워드 기반

Embedding Space Allocation with Angle-Norm Joint Classifiers for Few-Shot Class-Incremental Learning

2024-11-14 · Dunwei Tu, Huiyu Yi, Tieyi Zhang, Ruotong Li 외

Few-shot class-incremental learning (FSCIL) aims to continually learn new classes from only a few samples without forgetting previous ones, requiring intelligent agents to adapt to dynamic environments. FSCIL combines th…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningFew-Shot Learning+1

Bias Mitigating Few-Shot Class-Incremental Learning

2024-02-01 · Li-Jun Zhao, Zhen-Duo Chen, Zi-Chao Zhang, Xin Luo 외

Few-shot class-incremental learning (FSCIL) aims at recognizing novel classes continually with limited novel class samples. A mainstream baseline for FSCIL is first to train the whole model in the base session, then free…

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

Demystifying the Base and Novel Performances for Few-shot Class-incremental Learning

2022-06-18 · Jaehoon Oh, Se-Young Yun

Few-shot class-incremental learning (FSCIL) has addressed challenging real-world scenarios where unseen novel classes continually arrive with few samples. In these scenarios, it is required to develop a model that recogn…

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

Few-shot Class-incremental Audio Classification Using Stochastic Classifier

2023-06-03 · Yanxiong Li, Wenchang Cao, Jialong Li, Wei Xie 외

It is generally assumed that number of classes is fixed in current audio classification methods, and the model can recognize pregiven classes only. When new classes emerge, the model needs to be retrained with adequate s…

Audio ClassificationClassification

Active Class Selection for Few-Shot Class-Incremental Learning

2023-07-05 · Christopher McClurg, Ali Ayub, Harsh Tyagi, Sarah M. Rajtmajer 외

For real-world applications, robots will need to continually learn in their environments through limited interactions with their users. Toward this, previous works in few-shot class incremental learning (FSCIL) and activ…

class-incremental learningClass Incremental LearningFew-Shot Class-Incremental LearningIncremental Learning+1