TACLE: Task and Class-aware Exemplar-free Semi-supervised Class Incremental Learning

• URL: http://arxiv.org/abs/2407.08041v1
• Date: Wed, 10 Jul 2024 20:46:35 GMT
• Title: TACLE: Task and Class-aware Exemplar-free Semi-supervised Class Incremental Learning
• Authors: Jayateja Kalla, Rohit Kumar, Soma Biswas,
• Abstract summary: We propose a novel TACLE framework to address the problem of exemplar-free semi-supervised class incremental learning. In this scenario, at each new task, the model has to learn new classes from both labeled and unlabeled data. In addition to leveraging the capabilities of pre-trained models, TACLE proposes a novel task-adaptive threshold.
• Score: 16.734025446561695
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel TACLE (TAsk and CLass-awarE) framework to address the relatively unexplored and challenging problem of exemplar-free semi-supervised class incremental learning. In this scenario, at each new task, the model has to learn new classes from both (few) labeled and unlabeled data without access to exemplars from previous classes. In addition to leveraging the capabilities of pre-trained models, TACLE proposes a novel task-adaptive threshold, thereby maximizing the utilization of the available unlabeled data as incremental learning progresses. Additionally, to enhance the performance of the under-represented classes within each task, we propose a class-aware weighted cross-entropy loss. We also exploit the unlabeled data for classifier alignment, which further enhances the model performance. Extensive experiments on benchmark datasets, namely CIFAR10, CIFAR100, and ImageNet-Subset100 demonstrate the effectiveness of the proposed TACLE framework. We further showcase its effectiveness when the unlabeled data is imbalanced and also for the extreme case of one labeled example per class.

Related papers

• Uncertainty Aware Learning for Language Model Alignment [97.36361196793929]
  We propose uncertainty-aware learning (UAL) to improve the model alignment of different task scenarios. We implement UAL in a simple fashion -- adaptively setting the label smoothing value of training according to the uncertainty of individual samples. Experiments on widely used benchmarks demonstrate that our UAL significantly and consistently outperforms standard supervised fine-tuning.
  arXiv  Detail & Related papers  (2024-06-07T11:37:45Z)
• Diverse Teacher-Students for Deep Safe Semi-Supervised Learning under Class Mismatch [35.42630035488178]
  We introduce a novel framework named Diverse Teacher-Students (textbfDTS) By training both teacher-student models with all unlabeled samples, DTS can enhance the classification of seen classes while simultaneously improving the detection of unseen classes.
  arXiv  Detail & Related papers  (2024-05-25T06:54:43Z)
• Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning [44.91863420044712]
  In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlabeled data. We introduce 1) the adaptive synchronizing marginal loss which imposes class-specific negative margins to alleviate the model bias towards seen classes, and 2) the pseudo-label contrastive clustering which exploits pseudo-labels predicted by the model to group unlabeled data from the same category together. Our method balances the learning pace between seen and novel classes, achieving a remarkable 3% average accuracy increase on the ImageNet dataset.
  arXiv  Detail & Related papers  (2023-09-21T09:44:39Z)
• Few-Shot Class-Incremental Learning from an Open-Set Perspective [10.898784938875702]
  We explore the important task of Few-Shot Class-Incremental Learning (FSCIL) and its extreme data scarcity condition of one-shot. In ALICE, instead of the commonly used cross-entropy loss, we propose to use the angular penalty loss to obtain well-clustered features. Experiments on benchmark datasets, including CIFAR100, miniImageNet, and CUB200, demonstrate the improved performance of ALICE.
  arXiv  Detail & Related papers  (2022-07-30T05:42:48Z)
• Class-Aware Contrastive Semi-Supervised Learning [51.205844705156046]
  We propose a general method named Class-aware Contrastive Semi-Supervised Learning (CCSSL) to improve pseudo-label quality and enhance the model's robustness in the real-world setting. Our proposed CCSSL has significant performance improvements over the state-of-the-art SSL methods on the standard datasets CIFAR100 and STL10.
  arXiv  Detail & Related papers  (2022-03-04T12:18:23Z)
• CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learning [55.733193075728096]
  Modern deep neural networks can easily overfit to biased training data containing corrupted labels or class imbalance. Sample re-weighting methods are popularly used to alleviate this data bias issue. We propose a meta-model capable of adaptively learning an explicit weighting scheme directly from data.
  arXiv  Detail & Related papers  (2022-02-11T13:49:51Z)
• Novel Class Discovery in Semantic Segmentation [104.30729847367104]
  We introduce a new setting of Novel Class Discovery in Semantic (NCDSS) It aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes. In NCDSS, we need to distinguish the objects and background, and to handle the existence of multiple classes within an image. We propose the Entropy-based Uncertainty Modeling and Self-training (EUMS) framework to overcome noisy pseudo-labels.
  arXiv  Detail & Related papers  (2021-12-03T13:31:59Z)
• 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)
• Continual Learning From Unlabeled Data Via Deep Clustering [7.704949298975352]
  Continual learning aims to learn new tasks incrementally using less computation and memory resources instead of retraining the model from scratch whenever new task arrives. We introduce a new framework to make continual learning feasible in unsupervised mode by using pseudo label obtained from cluster assignments to update model.
  arXiv  Detail & Related papers  (2021-04-14T23:46:17Z)
• 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)
• A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm [18.670975246545208]
  Unsupervised embedding learning aims to extract good representation from data without the need for any manual labels. This paper proposes a new unsupervised embedding approach, called Super-AND, which extends the current state-of-the-art model. Super-AND outperforms all existing approaches and achieves an accuracy of 89.2% on the image classification task for CIFAR-10.
  arXiv  Detail & Related papers  (2020-02-26T13:22:04Z)

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.