Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning

By Kai Zhu, Wei Zhai, Yang Cao, Jiebo Luo, Zhengjun Zha. 2022

198 citations recorded by the source corpus.

Non-exemplar class-incremental learning is to recognize both the old and new classes when old class samples cannot be saved. It is a challenging task since representation optimization and feature retention can only be achieved under supervision from new classes. To address this problem, we propose a novel self-sustaining representation expansion scheme. Our scheme consists of a structure reorganization strategy that fuses main-branch expansion and side-branch updating to maintain the old features, and a main-branch distillation scheme to transfer the invariant knowledge. Furthermore, a prototype selection mechanism is proposed to enhance the discrimination between the old and new classes by selectively incorporating new samples into the distillation process. Extensive experiments on three benchmarks demonstrate significant incremental performance, outperforming the state-of-the-art methods by a margin of 3%, 3% and 6%, respectively.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Meta & Continual Learning

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, methodology): “Other methods exploit the class-wise statistics of feature representations to obtain a balanced classifier, such as by imposing the representations to be transferable and invariant (SPB [453], IL2A [509], SSRE [512], FeTrIL [333]), or compensating explicitly the representation shifts (SDC [484], RER”
FeTrIL: Feature Translation for Exemplar-Free Class-Incremental Learning (2022, methodology): “New classes are well predicted since models are learned with all new data and only a representation of past data [24, 31, 49].”
Incremental Nuclei Segmentation from Histopathological Images via Future-class Awareness and Compatibility-inspired Distillation (2024, background): “Architecture-based approaches [16, 38, 44] dynamically grow the network to extend model capacity for new tasks.”
Elastic Feature Consolidation for Cold Start Exemplar-free Incremental Learning (2024, methodology): “Specifically we consider EWC (Kirkpatrick et al., 2017), LwF (Li & Hoiem, 2017), PASS (Zhu et al., 2021b), Fusion (Toldo & Ozay, 2022), FeTrIL (Petit et al., 2023) and SSRE (Zhu et al., 2022).”
Class-Incremental Learning: A Survey (2023, methodology): “The optimization parameters of them are set according to the original paper since ViT has a different optimization preference to CNN.”
Resurrecting Old Classes with New Data for Exemplar-Free Continual Learning (2024, methodology): “This includes LwF [24], PASS [55], SSRE [56], FeTRIL [35] and Fe-CAM [11].”