Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor

• URL: http://arxiv.org/abs/2204.13349v1
• Date: Thu, 28 Apr 2022 08:41:51 GMT
• Title: Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor
• Authors: Yang Yang, Zhiying Cui, Junjie Xu, Changhong Zhong, Wei-Shi Zheng, Ruixuan Wang
• Abstract summary: Current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. Inspired by the process of learning new knowledge in human brains, we propose a Bayesian generative model for continual learning.
• Score: 55.9023096444383
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep learning has shown its human-level performance in various applications. However, current deep learning models are characterised by catastrophic forgetting of old knowledge when learning new classes. This poses a challenge particularly in intelligent diagnosis systems where initially only training data of a limited number of diseases are available. In this case, updating the intelligent system with data of new diseases would inevitably downgrade its performance on previously learned diseases. Inspired by the process of learning new knowledge in human brains, we propose a Bayesian generative model for continual learning built on a fixed pre-trained feature extractor. In this model, knowledge of each old class can be compactly represented by a collection of statistical distributions, e.g. with Gaussian mixture models, and naturally kept from forgetting in continual learning over time. Unlike existing class-incremental learning methods, the proposed approach is not sensitive to the continual learning process and can be additionally well applied to the data-incremental learning scenario. Experiments on multiple medical and natural image classification tasks showed that the proposed approach outperforms state-of-the-art approaches which even keep some images of old classes during continual learning of new classes.

Related papers

• From Uncertainty to Clarity: Uncertainty-Guided Class-Incremental Learning for Limited Biomedical Samples via Semantic Expansion [0.0]
  We propose a class-incremental learning method under limited samples in the biomedical field. Our method achieves optimal performance, surpassing state-of-the-art methods by as much as 53.54% in accuracy.
  arXiv  Detail & Related papers  (2024-09-12T05:22:45Z)
• Continual Learning in Medical Image Analysis: A Comprehensive Review of Recent Advancements and Future Prospects [5.417947115749931]
  Continual learning has emerged as a crucial approach for developing unified and sustainable deep models. This systematic review paper provides a comprehensive overview of the state-of-the-art in continual learning techniques applied to medical imaging analysis.
  arXiv  Detail & Related papers  (2023-12-28T13:16:03Z)
• Learning to Jump: Thinning and Thickening Latent Counts for Generative Modeling [69.60713300418467]
  Learning to jump is a general recipe for generative modeling of various types of data. We demonstrate when learning to jump is expected to perform comparably to learning to denoise, and when it is expected to perform better.
  arXiv  Detail & Related papers  (2023-05-28T05:38:28Z)
• SRIL: Selective Regularization for Class-Incremental Learning [5.810252620242912]
  Class-Incremental Learning aims to create an integrated model that balances plasticity and stability to overcome this challenge. We propose a selective regularization method that accepts new knowledge while maintaining previous knowledge. We validate the effectiveness of the proposed method through extensive experimental protocols using CIFAR-100, ImageNet-Subset, and ImageNet-Full.
  arXiv  Detail & Related papers  (2023-05-09T05:04:35Z)
• Adapter Learning in Pretrained Feature Extractor for Continual Learning of Diseases [66.27889778566734]
  Currently intelligent diagnosis systems lack the ability of continually learning to diagnose new diseases once deployed. In particular, updating an intelligent diagnosis system with training data of new diseases would cause catastrophic forgetting of old disease knowledge. An adapter-based Continual Learning framework called ACL is proposed to help effectively learn a set of new diseases.
  arXiv  Detail & Related papers  (2023-04-18T15:01:45Z)
• LifeLonger: A Benchmark for Continual Disease Classification [59.13735398630546]
  We introduce LifeLonger, a benchmark for continual disease classification on the MedMNIST collection. Task and class incremental learning of diseases address the issue of classifying new samples without re-training the models from scratch. Cross-domain incremental learning addresses the issue of dealing with datasets originating from different institutions while retaining the previously obtained knowledge.
  arXiv  Detail & Related papers  (2022-04-12T12:25:05Z)
• Relational Subsets Knowledge Distillation for Long-tailed Retinal Diseases Recognition [65.77962788209103]
  We propose class subset learning by dividing the long-tailed data into multiple class subsets according to prior knowledge. It enforces the model to focus on learning the subset-specific knowledge. The proposed framework proved to be effective for the long-tailed retinal diseases recognition task.
  arXiv  Detail & Related papers  (2021-04-22T13:39:33Z)
• Select-ProtoNet: Learning to Select for Few-Shot Disease Subtype Prediction [55.94378672172967]
  We focus on few-shot disease subtype prediction problem, identifying subgroups of similar patients. We introduce meta learning techniques to develop a new model, which can extract the common experience or knowledge from interrelated clinical tasks. Our new model is built upon a carefully designed meta-learner, called Prototypical Network, that is a simple yet effective meta learning machine for few-shot image classification.
  arXiv  Detail & Related papers  (2020-09-02T02:50:30Z)
• Self-Supervised Learning Aided Class-Incremental Lifelong Learning [17.151579393716958]
  We study the issue of catastrophic forgetting in class-incremental learning (Class-IL) In training procedure of Class-IL, as the model has no knowledge about following tasks, it would only extract features necessary for tasks learned so far, whose information is insufficient for joint classification. We propose to combine self-supervised learning, which can provide effective representations without requiring labels, with Class-IL to partly get around this problem.
  arXiv  Detail & Related papers  (2020-06-10T15:15:27Z)

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.