SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model

• URL: http://arxiv.org/abs/2303.05118v4
• Date: Mon, 9 Oct 2023 15:50:00 GMT
• Title: SLCA: Slow Learner with Classifier Alignment for Continual Learning on a Pre-trained Model
• Authors: Gengwei Zhang, Liyuan Wang, Guoliang Kang, Ling Chen, Yunchao Wei
• Abstract summary: We present an extensive analysis for continual learning on a pre-trained model (CLPM) We propose a simple but extremely effective approach named Slow Learner with Alignment (SLCA) Across a variety of scenarios, our proposal provides substantial improvements for CLPM.
• Score: 73.80068155830708
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The goal of continual learning is to improve the performance of recognition models in learning sequentially arrived data. Although most existing works are established on the premise of learning from scratch, growing efforts have been devoted to incorporating the benefits of pre-training. However, how to adaptively exploit the pre-trained knowledge for each incremental task while maintaining its generalizability remains an open question. In this work, we present an extensive analysis for continual learning on a pre-trained model (CLPM), and attribute the key challenge to a progressive overfitting problem. Observing that selectively reducing the learning rate can almost resolve this issue in the representation layer, we propose a simple but extremely effective approach named Slow Learner with Classifier Alignment (SLCA), which further improves the classification layer by modeling the class-wise distributions and aligning the classification layers in a post-hoc fashion. Across a variety of scenarios, our proposal provides substantial improvements for CLPM (e.g., up to 49.76%, 50.05%, 44.69% and 40.16% on Split CIFAR-100, Split ImageNet-R, Split CUB-200 and Split Cars-196, respectively), and thus outperforms state-of-the-art approaches by a large margin. Based on such a strong baseline, critical factors and promising directions are analyzed in-depth to facilitate subsequent research. Code has been made available at: https://github.com/GengDavid/SLCA.

Related papers

• SLCA++: Unleash the Power of Sequential Fine-tuning for Continual Learning with Pre-training [68.7896349660824]
  We present an in-depth analysis of the progressive overfitting problem from the lens of Seq FT. Considering that the overly fast representation learning and the biased classification layer constitute this particular problem, we introduce the advanced Slow Learner with Alignment (S++) framework. Our approach involves a Slow Learner to selectively reduce the learning rate of backbone parameters, and a Alignment to align the disjoint classification layers in a post-hoc fashion.
  arXiv  Detail & Related papers  (2024-08-15T17:50:07Z)
• 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)
• RanPAC: Random Projections and Pre-trained Models for Continual Learning [59.07316955610658]
  Continual learning (CL) aims to learn different tasks (such as classification) in a non-stationary data stream without forgetting old ones. We propose a concise and effective approach for CL with pre-trained models.
  arXiv  Detail & Related papers  (2023-07-05T12:49:02Z)
• 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)
• Self-Supervised Class Incremental Learning [51.62542103481908]
  Existing Class Incremental Learning (CIL) methods are based on a supervised classification framework sensitive to data labels. When updating them based on the new class data, they suffer from catastrophic forgetting: the model cannot discern old class data clearly from the new. In this paper, we explore the performance of Self-Supervised representation learning in Class Incremental Learning (SSCIL) for the first time.
  arXiv  Detail & Related papers  (2021-11-18T06:58:19Z)
• Few-Shot Incremental Learning with Continually Evolved Classifiers [46.278573301326276]
  Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. We propose a Continually Evolved CIF ( CEC) that employs a graph model to propagate context information between classifiers for adaptation.
  arXiv  Detail & Related papers  (2021-04-07T10:54:51Z)
• Cognitively-Inspired Model for Incremental Learning Using a Few Examples [11.193504036335503]
  Incremental learning attempts to develop a classifier which learns continuously from a stream of data segregated into different classes. Deep learning approaches suffer from catastrophic forgetting when learning classes incrementally, while most incremental learning approaches require a large amount of training data per class. We propose a novel approach inspired by the concept learning model of the hippocampus and the neocortex that represents each image class as centroids.
  arXiv  Detail & Related papers  (2020-02-27T19:52:42Z)

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.