Few-Shot Class-Incremental Learning with Prior Knowledge
- URL: http://arxiv.org/abs/2402.01201v1
- Date: Fri, 2 Feb 2024 08:05:35 GMT
- Title: Few-Shot Class-Incremental Learning with Prior Knowledge
- Authors: Wenhao Jiang, Duo Li, Menghan Hu, Guangtao Zhai, Xiaokang Yang,
Xiao-Ping Zhang
- Abstract summary: 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.
- Score: 94.95569068211195
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: To tackle the issues of catastrophic forgetting and overfitting in few-shot
class-incremental learning (FSCIL), previous work has primarily concentrated on
preserving the memory of old knowledge during the incremental phase. The role
of pre-trained model in shaping the effectiveness of incremental learning is
frequently underestimated in these studies. Therefore, to enhance the
generalization ability of the pre-trained model, we propose Learning with Prior
Knowledge (LwPK) by introducing nearly free prior knowledge from a few
unlabeled data of subsequent incremental classes. We cluster unlabeled
incremental class samples to produce pseudo-labels, then jointly train these
with labeled base class samples, effectively allocating embedding space for
both old and new class data. Experimental results indicate that LwPK
effectively enhances the model resilience against catastrophic forgetting, with
theoretical analysis based on empirical risk minimization and class distance
measurement corroborating its operational principles. The source code of LwPK
is publicly available at: \url{https://github.com/StevenJ308/LwPK}.
Related papers
- An Efficient Replay for Class-Incremental Learning with Pre-trained Models [0.0]
In class-incremental learning, the steady state among the weight guided by each class center is disrupted, which is significantly correlated with forgetting.
We propose a new method to overcoming forgetting.
arXiv Detail & Related papers (2024-08-15T11:26:28Z) - Bias Mitigating Few-Shot Class-Incremental Learning [17.185744533050116]
Few-shot class-incremental learning aims at recognizing novel classes continually with limited novel class samples.
Recent methods somewhat alleviate the accuracy imbalance between base and incremental classes by fine-tuning the feature extractor in the incremental sessions.
We propose a novel method to mitigate model bias of the FSCIL problem during training and inference processes.
arXiv Detail & Related papers (2024-02-01T10:37:41Z) - An Analysis of Initial Training Strategies for Exemplar-Free
Class-Incremental Learning [36.619804184427245]
Class-Incremental Learning (CIL) aims to build classification models from data streams.
Due to catastrophic forgetting, CIL is particularly challenging when examples from past classes cannot be stored.
Use of models pre-trained in a self-supervised way on large amounts of data has recently gained momentum.
arXiv Detail & Related papers (2023-08-22T14:06:40Z) - 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) - 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) - Mitigating Forgetting in Online Continual Learning via Contrasting
Semantically Distinct Augmentations [22.289830907729705]
Online continual learning (OCL) aims to enable model learning from a non-stationary data stream to continuously acquire new knowledge as well as retain the learnt one.
Main challenge comes from the "catastrophic forgetting" issue -- the inability to well remember the learnt knowledge while learning the new ones.
arXiv Detail & Related papers (2022-11-10T05:29:43Z) - Adaptive Distribution Calibration for Few-Shot Learning with
Hierarchical Optimal Transport [78.9167477093745]
We propose a novel distribution calibration method by learning the adaptive weight matrix between novel samples and base classes.
Experimental results on standard benchmarks demonstrate that our proposed plug-and-play model outperforms competing approaches.
arXiv Detail & Related papers (2022-10-09T02:32:57Z) - SURF: Semi-supervised Reward Learning with Data Augmentation for
Feedback-efficient Preference-based Reinforcement Learning [168.89470249446023]
We present SURF, a semi-supervised reward learning framework that utilizes a large amount of unlabeled samples with data augmentation.
In order to leverage unlabeled samples for reward learning, we infer pseudo-labels of the unlabeled samples based on the confidence of the preference predictor.
Our experiments demonstrate that our approach significantly improves the feedback-efficiency of the preference-based method on a variety of locomotion and robotic manipulation tasks.
arXiv Detail & Related papers (2022-03-18T16:50:38Z) - 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) - Class-incremental Learning with Rectified Feature-Graph Preservation [24.098892115785066]
A central theme of this paper is to learn new classes that arrive in sequential phases over time.
We propose a weighted-Euclidean regularization for old knowledge preservation.
We show how it can work with binary cross-entropy to increase class separation for effective learning of new classes.
arXiv Detail & Related papers (2020-12-15T07:26:04Z)
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.