First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning

By Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino, Rahaf Aljundi, Richard E. Turner. 2023

60 citations recorded by the source corpus.

In Class-Incremental Learning (CIL) an image classification system is exposed to new classes in each learning session and must be updated incrementally. Methods approaching this problem have updated both the classification head and the feature extractor body at each session of CIL. In this work, we develop a baseline method, First Session Adaptation (FSA), that sheds light on the efficacy of existing CIL approaches, and allows us to assess the relative performance contributions from head and body adaption. FSA adapts a pre-trained neural network body only on the first learning session and fixes it thereafter; a head based on linear discriminant analysis (LDA), is then placed on top of the adapted body, allowing exact updates through CIL. FSA is replay-free i.e. it does not memorize examples from previous sessions of continual learning. To empirically motivate FSA, we first consider a diverse selection of 22 image-classification datasets, evaluating different heads and body adaptation techniques in high/low-shot offline settings. We find that the LDA head performs well and supports CIL out-of-the-box. We also find that Featurewise Layer Modulation (FiLM) adapters are highly effective in the few-shot setting, and full-body adaption in the high-shot setting. Second, we empirically investigate various CIL settings including high-shot CIL and few-shot CIL, including settings that have previously been used in the literature. We show that FSA significantly improves over the state-of-the-art in 15 of the 16 settings considered. FSA with FiLM adapters is especially performant in the few-shot setting. These results indicate that current approaches to continuous body adaptation are not working as expected. Finally, we propose a measure that can be applied to a set of unlabelled inputs which is predictive of the benefits of body adaptation.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging, 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 Radiology, Nuclear Medicine and Imaging

In Meta & Continual Learning

Citations in the corpus

A Comprehensive Survey of Continual Learning: Theory, Method and Application (2023, background): “Besides, by saving prototypes, appendinganearestclassmean(NCM)classiﬁertothebackbone hasprovedtobeastrongbaseline[210],[211],whichcanbe furtherenhancedbytransferlearningtechniquessuchasthe FiLMadapter[212].Asforoptimizingan Asforoptimizingan updatable backbone, F2M [84] searches for ﬂat local minima”
Elastic Feature Consolidation for Cold Start Exemplar-free Incremental Learning (2024, methodology): “Most functional regularization approaches use feature distillation (Zhu et al., 2021a; Yu et al., 2020), or even freeze the feature extractor after the first task (Petit et al., 2023; Belouadah & Popescu, 2018; Panos et al., 2023), greatly reducing the plasticity of the network.”