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

• URL: http://arxiv.org/abs/2303.13199v3
• Date: Fri, 12 Jan 2024 12:31:00 GMT
• Title: First Session Adaptation: A Strong Replay-Free Baseline for Class-Incremental Learning
• Authors: Aristeidis Panos, Yuriko Kobe, Daniel Olmeda Reino, Rahaf Aljundi, Richard E. Turner
• Abstract summary: First Session Adaptation (FSA) adapts a pre-trained neural network body only on the first learning session and fixes it thereafter. FSA significantly improves over the state-of-the-art in 15 of the 16 settings considered. We propose a measure that can be applied to a set of unlabelled inputs which is predictive of the benefits of body adaptation.
• Score: 26.88977803220915
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Rethinking Few-Shot Adaptation of Vision-Language Models in Two Stages [28.834044800595716]
  In Few-Shot Adaptation (FSA), data are insufficient to fit a large number of parameters, rendering the above impractical. We call this scheme Two-Stage Few-Shot Adaptation (2SFS) We show that 2SFS matches or surpasses the state-of-the-art, while established methods degrade significantly across settings.
  arXiv  Detail & Related papers  (2025-03-14T17:24:01Z)
• CALA: A Class-Aware Logit Adapter for Few-Shot Class-Incremental Learning [9.963958892953876]
  We propose a lightweight adapter that learns to rectify biased predictions through a pseudo-incremental learning paradigm. Our method involves a lightweight adapter that learns to rectify biased predictions through a pseudo-incremental learning paradigm.
  arXiv  Detail & Related papers  (2024-12-17T08:21:46Z)
• Learning Prompt with Distribution-Based Feature Replay for Few-Shot Class-Incremental Learning [56.29097276129473]
  We propose a simple yet effective framework, named Learning Prompt with Distribution-based Feature Replay (LP-DiF) To prevent the learnable prompt from forgetting old knowledge in the new session, we propose a pseudo-feature replay approach. When progressing to a new session, pseudo-features are sampled from old-class distributions combined with training images of the current session to optimize the prompt.
  arXiv  Detail & Related papers  (2024-01-03T07:59:17Z)
• Class Incremental Learning with Pre-trained Vision-Language Models [59.15538370859431]
  We propose an approach to exploiting pre-trained vision-language models (e.g. CLIP) that enables further adaptation. Experiments on several conventional benchmarks consistently show a significant margin of improvement over the current state-of-the-art.
  arXiv  Detail & Related papers  (2023-10-31T10:45:03Z)
• Strong Baselines for Parameter Efficient Few-Shot Fine-tuning [50.83426196335385]
  Few-shot classification (FSC) entails learning novel classes given only a few examples per class after a pre-training (or meta-training) phase. Recent works have shown that simply fine-tuning a pre-trained Vision Transformer (ViT) on new test classes is a strong approach for FSC. Fine-tuning ViTs, however, is expensive in time, compute and storage. This has motivated the design of parameter efficient fine-tuning (PEFT) methods which fine-tune only a fraction of the Transformer's parameters.
  arXiv  Detail & Related papers  (2023-04-04T16:14:39Z)
• Incremental Few-Shot Object Detection via Simple Fine-Tuning Approach [6.808112517338073]
  iFSD incrementally learns novel classes using only a few examples without revisiting base classes. We propose a simple fine-tuning-based approach, the Incremental Two-stage Fine-tuning Approach (iTFA) for iFSD. iTFA achieves competitive performance in COCO and shows a 30% higher AP accuracy than meta-learning methods in the LVIS dataset.
  arXiv  Detail & Related papers  (2023-02-20T05:48:46Z)
• Class-Incremental Learning with Strong Pre-trained Models [97.84755144148535]
  Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes) We explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. Our proposed method is robust and generalizes to all analyzed CIL settings.
  arXiv  Detail & Related papers  (2022-04-07T17:58:07Z)
• Learning What Not to Segment: A New Perspective on Few-Shot Segmentation [63.910211095033596]
  Recently few-shot segmentation (FSS) has been extensively developed. This paper proposes a fresh and straightforward insight to alleviate the problem. In light of the unique nature of the proposed approach, we also extend it to a more realistic but challenging setting.
  arXiv  Detail & Related papers  (2022-03-15T03:08:27Z)
• No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Data [78.69828864672978]
  A central challenge in training classification models in the real-world federated system is learning with non-IID data. We propose a novel and simple algorithm called Virtual Representations (CCVR), which adjusts the classifier using virtual representations sampled from an approximated ssian mixture model. Experimental results demonstrate that CCVR state-of-the-art performance on popular federated learning benchmarks including CIFAR-10, CIFAR-100, and CINIC-10.
  arXiv  Detail & Related papers  (2021-06-09T12:02:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.