FCS: Feature Calibration and Separation for Non-Exemplar Class Incremental Learning

2024-01-01 · CVPR 2024 1 · Qiwei Li, Yuxin Peng, Jiahuan Zhou

Non-Exemplar Class Incremental Learning (NECIL) involves learning a classification model on a sequence of data without access to exemplars from previously encountered old classes. Such a stringent constraint always leads to catastrophic forgetting of the learned knowledge. Currently existing methods either employ knowledge distillation techniques or preserved class prototypes to sustain prior knowledge. However two critical issues still persist. On the one hand as the model is continually updated the preserved prototypes of old classes will inevitably derive from the suitable location in the feature space of the new model. On the other hand due to the lack of exemplars the features of new classes will take the place of similar old classes which breaks the classification boundary. To address these challenges we propose a Feature Calibration and Separation (FCS) method for NECIL. Our approach comprises a Feature Calibration Network (FCN) that adapts prototypes of old classes to the new model via optimal transport learning approximating the drift of prototypes caused by model evolution. Additionally we also propose a Prototype-Involved Contrastive Loss (PIC) that enhances feature separation among different classes. Specifically to mitigate the boundary distortion arising from the interplay of classes from different learning stages prototypes are involved in pushing the feature of new classes away from the old classes. Extensive experiments on three datasets with different settings have demonstrated the superiority of our FCS method against the state-of-the-art class incremental learning approaches. Code is available at https://github.com/zhoujiahuan1991/CVPR2024-FCS.

📄 PDF Abstract BibTeX

Code (1)

zhoujiahuan1991/cvpr2024-fcs 공식 구현 pytorch

Tasks

class-incremental learning Class Incremental Learning Incremental Learning Knowledge Distillation

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

T-CIL: Temperature Scaling using Adversarial Perturbation for Calibration in Class-Incremental Learning

2025-03-28 · CVPR 2025 1 · Seong-Hyeon Hwang, Minsu Kim, Steven Euijong Whang

We study model confidence calibration in class-incremental learning, where models learn from sequential tasks with different class sets. While existing works primarily focus on accuracy, maintaining calibrated confidence…

class-incremental learning Class Incremental Learning Incremental Learning

On the Discrimination and Consistency for Exemplar-Free Class Incremental Learning

2025-01-26 · Tianqi Wang, Jingcai Guo, Depeng Li, Zhi Chen

Exemplar-free class incremental learning (EF-CIL) is a nontrivial task that requires continuously enriching model capability with new classes while maintaining previously learned knowledge without storing and replaying a…

class-incremental learning Class Incremental Learning Exemplar-Free Incremental Learning

FeTrIL++: Feature Translation for Exemplar-Free Class-Incremental Learning with Hill-Climbing

2024-03-12 · Eduard Hogea, Adrian Popescu, Darian Onchis, Grégoire Petit

Exemplar-free class-incremental learning (EFCIL) poses significant challenges, primarily due to catastrophic forgetting, necessitating a delicate balance between stability and plasticity to accurately recognize both new …

class-incremental learning Class Incremental Learning Exemplar-Free Incremental Learning

Diffusion Model Meets Non-Exemplar Class-Incremental Learning and Beyond

2024-08-06 · Jichuan Zhang, YaLi Li, Xin Liu, Shengjin Wang

Non-exemplar class-incremental learning (NECIL) is to resist catastrophic forgetting without saving old class samples. Prior methodologies generally employ simple rules to generate features for replaying, suffering from …

class-incremental learning Class Incremental Learning Exemplar-Free Incremental Learning+2

FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning

2022-11-23 · Grégoire Petit, Adrian Popescu, Hugo Schindler, David Picard 외

Exemplar-free class-incremental learning is very challenging due to the negative effect of catastrophic forgetting. A balance between stability and plasticity of the incremental process is needed in order to obtain good …

class-incremental learning Class Incremental Learning Exemplar-Free Incremental Learning+1