Few-Shot Class-Incremental Learning from an Open-Set Perspective

By Can Peng, Kun Zhao, Tianren Wang, Meng Li, Brian C. Lovell. 2022

151 citations recorded by the source corpus.

The continual appearance of new objects in the visual world poses considerable challenges for current deep learning methods in real-world deployments. The challenge of new task learning is often exacerbated by the scarcity of data for the new categories due to rarity or cost. Here we explore the important task of Few-Shot Class-Incremental Learning (FSCIL) and its extreme data scarcity condition of one-shot. An ideal FSCIL model needs to perform well on all classes, regardless of their presentation order or paucity of data. It also needs to be robust to open-set real-world conditions and be easily adapted to the new tasks that always arise in the field. In this paper, we first reevaluate the current task setting and propose a more comprehensive and practical setting for the FSCIL task. Then, inspired by the similarity of the goals for FSCIL and modern face recognition systems, we propose our method -- Augmented Angular Loss Incremental Classification or ALICE. In ALICE, instead of the commonly used cross-entropy loss, we propose to use the angular penalty loss to obtain well-clustered features. As the obtained features not only need to be compactly clustered but also diverse enough to maintain generalization for future incremental classes, we further discuss how class augmentation, data augmentation, and data balancing affect classification performance. Experiments on benchmark datasets, including CIFAR100, miniImageNet, and CUB200, demonstrate the improved performance of ALICE over the state-of-the-art FSCIL methods.

Subfields: Artificial Intelligence, 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 Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, neutral): “…featurespacewithvirtualprototypesforfutureclasses[256],us-ingangularpenaltylosswithdataaugmentation[257],providing extraconstraintsfrommargin-basedrepresentations[258],etc. Thesecondistoobtainanadaptiveclassiﬁerfromasequence of novel classes, such…”
A Survey on Few-Shot Class-Incremental Learning (2023, background): “In the majority of FSCIL experiments (Cheraghian et al., 2021c; Chi et al., 2022; Liu et al., 2022b; Peng et al., 2022; SHI et al., 2021; Tao et al., 2020; Yang et al., 2022; Zhang et al., 2021; Zheng and Zhang, 2021; Zhou et al., 2022b; Zhu et al., 2021a), the three image classification datasets…”
Pre-trained Vision and Language Transformers are Few-Shot Incremental Learners (2024, methodology): “Feature and feature space-based methods [2, 12, 23, 30, 41, 42] enable the model to adapt to new classes better and improve the generalization ability of feature extractors for new classes.”
Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class Incremental Learning (2023, methodology): “Although we do not surpass ALICE in the last session on CUB-200, we still have the best average accuracy among all methods.”