CCSI: Continual Class-Specific Impression for Data-free Class Incremental Learning

• URL: http://arxiv.org/abs/2406.05631v1
• Date: Sun, 9 Jun 2024 03:52:21 GMT
• Title: CCSI: Continual Class-Specific Impression for Data-free Class Incremental Learning
• Authors: Sana Ayromlou, Teresa Tsang, Purang Abolmaesumi, Xiaoxiao Li,
• Abstract summary: Class incremental learning offers a promising solution by adapting a deep network trained on specific disease classes to handle new diseases. Prior proposed methodologies to overcome this require perpetual storage of previous samples. We propose a novel data-free class incremental learning framework that utilizes data synthesis on learned classes instead of data storage from previous classes.
• Score: 22.37848405465699
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In real-world clinical settings, traditional deep learning-based classification methods struggle with diagnosing newly introduced disease types because they require samples from all disease classes for offline training. Class incremental learning offers a promising solution by adapting a deep network trained on specific disease classes to handle new diseases. However, catastrophic forgetting occurs, decreasing the performance of earlier classes when adapting the model to new data. Prior proposed methodologies to overcome this require perpetual storage of previous samples, posing potential practical concerns regarding privacy and storage regulations in healthcare. To this end, we propose a novel data-free class incremental learning framework that utilizes data synthesis on learned classes instead of data storage from previous classes. Our key contributions include acquiring synthetic data known as Continual Class-Specific Impression (CCSI) for previously inaccessible trained classes and presenting a methodology to effectively utilize this data for updating networks when introducing new classes. We obtain CCSI by employing data inversion over gradients of the trained classification model on previous classes starting from the mean image of each class inspired by common landmarks shared among medical images and utilizing continual normalization layers statistics as a regularizer in this pixel-wise optimization process. Subsequently, we update the network by combining the synthesized data with new class data and incorporate several losses, including an intra-domain contrastive loss to generalize the deep network trained on the synthesized data to real data, a margin loss to increase separation among previous classes and new ones, and a cosine-normalized cross-entropy loss to alleviate the adverse effects of imbalanced distributions in training data.

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 Domain Incremental Learning for Privacy-aware Digital Pathology [3.6630930118966814]
  Continual learning (CL) techniques aim to reduce the forgetting of past data when learning new data with distributional shift conditions. We develop a Generative Latent Replay-based CL (GLRCL) approach to store past data and perform latent replay with new data.
  arXiv  Detail & Related papers  (2024-09-10T12:21:54Z)
• Few-Shot Class-Incremental Learning with Prior Knowledge [94.95569068211195]
  We propose Learning with Prior Knowledge (LwPK) to enhance the generalization ability of the pre-trained model. Experimental results indicate that LwPK effectively enhances the model resilience against catastrophic forgetting.
  arXiv  Detail & Related papers  (2024-02-02T08:05:35Z)
• TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization [89.54947228958494]
  This paper focuses on the fine-tuning of an adversarially pre-trained model in various classification tasks. We propose a novel statistics-based approach, Two-WIng NormliSation (TWINS) fine-tuning framework. TWINS is shown to be effective on a wide range of image classification datasets in terms of both generalization and robustness.
  arXiv  Detail & Related papers  (2023-03-20T14:12:55Z)
• Prototypical quadruplet for few-shot class incremental learning [24.814045065163135]
  We propose a novel method that improves classification robustness by identifying a better embedding space using an improved contrasting loss. Our approach retains previously acquired knowledge in the embedding space, even when trained with new classes. We demonstrate the effectiveness of our method by showing that the embedding space remains intact after training the model with new classes and outperforms existing state-of-the-art algorithms in terms of accuracy across different sessions.
  arXiv  Detail & Related papers  (2022-11-05T17:19:14Z)
• Class Impression for Data-free Incremental Learning [20.23329169244367]
  Deep learning-based classification approaches require collecting all samples from all classes in advance and are trained offline. This paradigm may not be practical in real-world clinical applications, where new classes are incrementally introduced through the addition of new data. We propose a novel data-free class incremental learning framework that first synthesizes data from the model trained on previous classes to generate a ours.
  arXiv  Detail & Related papers  (2022-06-26T06:20:17Z)
• Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractor [55.9023096444383]
  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.
  arXiv  Detail & Related papers  (2022-04-28T08:41:51Z)
• 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)
• Bridging Non Co-occurrence with Unlabeled In-the-wild Data for Incremental Object Detection [56.22467011292147]
  Several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection. Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novel classes. We propose the use of unlabeled in-the-wild data to bridge the non-occurrence caused by the missing base classes during the training of additional novel classes.
  arXiv  Detail & Related papers  (2021-10-28T10:57:25Z)
• Learning Adaptive Embedding Considering Incremental Class [55.21855842960139]
  Class-Incremental Learning (CIL) aims to train a reliable model with the streaming data, which emerges unknown classes sequentially. Different from traditional closed set learning, CIL has two main challenges: 1) Novel class detection. After the novel classes are detected, the model needs to be updated without re-training using entire previous data.
  arXiv  Detail & Related papers  (2020-08-31T04:11:24Z)
• Move-to-Data: A new Continual Learning approach with Deep CNNs, Application for image-class recognition [0.0]
  It is necessary to pre-train the model at a "training recording phase" and then adjust it to the new coming data. We propose a fast continual learning layer at the end of the neuronal network.
  arXiv  Detail & Related papers  (2020-06-12T13:04:58Z)

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.