Enhancing Visual Continual Learning with Language-Guided Supervision

• URL: http://arxiv.org/abs/2403.16124v1
• Date: Sun, 24 Mar 2024 12:41:58 GMT
• Title: Enhancing Visual Continual Learning with Language-Guided Supervision
• Authors: Bolin Ni, Hongbo Zhao, Chenghao Zhang, Ke Hu, Gaofeng Meng, Zhaoxiang Zhang, Shiming Xiang,
• Abstract summary: Continual learning aims to empower models to learn new tasks without forgetting previously acquired knowledge. We argue that the scarce semantic information conveyed by the one-hot labels hampers the effective knowledge transfer across tasks. Specifically, we use PLMs to generate semantic targets for each class, which are frozen and serve as supervision signals.
• Score: 76.38481740848434
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Continual learning (CL) aims to empower models to learn new tasks without forgetting previously acquired knowledge. Most prior works concentrate on the techniques of architectures, replay data, regularization, \etc. However, the category name of each class is largely neglected. Existing methods commonly utilize the one-hot labels and randomly initialize the classifier head. We argue that the scarce semantic information conveyed by the one-hot labels hampers the effective knowledge transfer across tasks. In this paper, we revisit the role of the classifier head within the CL paradigm and replace the classifier with semantic knowledge from pretrained language models (PLMs). Specifically, we use PLMs to generate semantic targets for each class, which are frozen and serve as supervision signals during training. Such targets fully consider the semantic correlation between all classes across tasks. Empirical studies show that our approach mitigates forgetting by alleviating representation drifting and facilitating knowledge transfer across tasks. The proposed method is simple to implement and can seamlessly be plugged into existing methods with negligible adjustments. Extensive experiments based on eleven mainstream baselines demonstrate the effectiveness and generalizability of our approach to various protocols. For example, under the class-incremental learning setting on ImageNet-100, our method significantly improves the Top-1 accuracy by 3.2\% to 6.1\% while reducing the forgetting rate by 2.6\% to 13.1\%.

Related papers

• EMPL: A novel Efficient Meta Prompt Learning Framework for Few-shot Unsupervised Domain Adaptation [22.586094394391747]
  We propose a novel Efficient Meta Prompt Learning Framework for FS-UDA. Within this framework, we use pre-trained CLIP model as the feature learning base model. Our method has the large improvement of at least 15.4% on 5-way 1-shot and 8.7% on 5-way 5-shot, compared with the state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-07-04T17:13:06Z)
• Improving Zero-shot Generalization of Learned Prompts via Unsupervised Knowledge Distillation [14.225723195634941]
  We propose a novel approach to prompt learning based on unsupervised knowledge distillation from more powerful models. Our approach, which we call Knowledge Distillation Prompt Learning (KDPL), can be integrated into existing prompt learning techniques.
  arXiv  Detail & Related papers  (2024-07-03T12:24:40Z)
• Adaptive Rentention & Correction for Continual Learning [114.5656325514408]
  A common problem in continual learning is the classification layer's bias towards the most recent task. We name our approach Adaptive Retention & Correction (ARC) ARC achieves an average performance increase of 2.7% and 2.6% on the CIFAR-100 and Imagenet-R datasets.
  arXiv  Detail & Related papers  (2024-05-23T08:43:09Z)
• Semantic Segmentation with Active Semi-Supervised Representation Learning [23.79742108127707]
  We train an effective semantic segmentation algorithm with significantly lesser labeled data. We extend the prior state-of-the-art S4AL algorithm by replacing its mean teacher approach for semi-supervised learning with a self-training approach. We evaluate our method on CamVid and CityScapes datasets, the de-facto standards for active learning for semantic segmentation.
  arXiv  Detail & Related papers  (2022-10-16T00:21:43Z)
• 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)
• Partial Is Better Than All: Revisiting Fine-tuning Strategy for Few-shot Learning [76.98364915566292]
  A common practice is to train a model on the base set first and then transfer to novel classes through fine-tuning. We propose to transfer partial knowledge by freezing or fine-tuning particular layer(s) in the base model. We conduct extensive experiments on CUB and mini-ImageNet to demonstrate the effectiveness of our proposed method.
  arXiv  Detail & Related papers  (2021-02-08T03:27:05Z)
• ProtoDA: Efficient Transfer Learning for Few-Shot Intent Classification [21.933876113300897]
  We adopt an alternative approach by transfer learning on an ensemble of related tasks using prototypical networks under the meta-learning paradigm. Using intent classification as a case study, we demonstrate that increasing variability in training tasks can significantly improve classification performance.
  arXiv  Detail & Related papers  (2021-01-28T00:19:13Z)
• CLASTER: Clustering with Reinforcement Learning for Zero-Shot Action Recognition [52.66360172784038]
  We propose a clustering-based model, which considers all training samples at once, instead of optimizing for each instance individually. We call the proposed method CLASTER and observe that it consistently improves over the state-of-the-art in all standard datasets.
  arXiv  Detail & Related papers  (2021-01-18T12:46:24Z)
• Incremental Embedding Learning via Zero-Shot Translation [65.94349068508863]
  Current state-of-the-art incremental learning methods tackle catastrophic forgetting problem in traditional classification networks. We propose a novel class-incremental method for embedding network, named as zero-shot translation class-incremental method (ZSTCI) In addition, ZSTCI can easily be combined with existing regularization-based incremental learning methods to further improve performance of embedding networks.
  arXiv  Detail & Related papers  (2020-12-31T08:21:37Z)
• iTAML: An Incremental Task-Agnostic Meta-learning Approach [123.10294801296926]
  Humans can continuously learn new knowledge as their experience grows. Previous learning in deep neural networks can quickly fade out when they are trained on a new task. We introduce a novel meta-learning approach that seeks to maintain an equilibrium between all encountered tasks.
  arXiv  Detail & Related papers  (2020-03-25T21:42:48Z)

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.