Class Balance Matters to Active Class-Incremental Learning

• URL: http://arxiv.org/abs/2412.06642v1
• Date: Mon, 09 Dec 2024 16:37:27 GMT
• Title: Class Balance Matters to Active Class-Incremental Learning
• Authors: Zitong Huang, Ze Chen, Yuanze Li, Bowen Dong, Erjin Zhou, Yong Liu, Rick Siow Mong Goh, Chun-Mei Feng, Wangmeng Zuo,
• Abstract summary: We aim to start from a pool of large-scale unlabeled data and then annotate the most informative samples for incremental learning. We propose Class-Balanced Selection (CBS) strategy to achieve both class balance and informativeness in chosen samples. Our CBS can be plugged and played into those CIL methods which are based on pretrained models with prompts tunning technique.
• Score: 61.11786214164405
• License:
• Abstract: Few-Shot Class-Incremental Learning has shown remarkable efficacy in efficient learning new concepts with limited annotations. Nevertheless, the heuristic few-shot annotations may not always cover the most informative samples, which largely restricts the capability of incremental learner. We aim to start from a pool of large-scale unlabeled data and then annotate the most informative samples for incremental learning. Based on this premise, this paper introduces the Active Class-Incremental Learning (ACIL). The objective of ACIL is to select the most informative samples from the unlabeled pool to effectively train an incremental learner, aiming to maximize the performance of the resulting model. Note that vanilla active learning algorithms suffer from class-imbalanced distribution among annotated samples, which restricts the ability of incremental learning. To achieve both class balance and informativeness in chosen samples, we propose Class-Balanced Selection (CBS) strategy. Specifically, we first cluster the features of all unlabeled images into multiple groups. Then for each cluster, we employ greedy selection strategy to ensure that the Gaussian distribution of the sampled features closely matches the Gaussian distribution of all unlabeled features within the cluster. Our CBS can be plugged and played into those CIL methods which are based on pretrained models with prompts tunning technique. Extensive experiments under ACIL protocol across five diverse datasets demonstrate that CBS outperforms both random selection and other SOTA active learning approaches. Code is publicly available at https://github.com/1170300714/CBS.

Related papers

• CVOCSemRPL: Class-Variance Optimized Clustering, Semantic Information Injection and Restricted Pseudo Labeling based Improved Semi-Supervised Few-Shot Learning [4.3149314441871205]
  Unlabeled samples are generally cheaper to obtain and can be used to improve the few-shot learning performance of the model. We propose an approach for semi-supervised few-shot learning that performs a class-variance optimized clustering. We experimentally demonstrate that our proposed approach significantly outperforms recent state-of-the-art methods on the benchmark datasets.
  arXiv  Detail & Related papers  (2025-01-24T11:14:35Z)
• One-bit Supervision for Image Classification: Problem, Solution, and Beyond [114.95815360508395]
  This paper presents one-bit supervision, a novel setting of learning with fewer labels, for image classification. We propose a multi-stage training paradigm and incorporate negative label suppression into an off-the-shelf semi-supervised learning algorithm. In multiple benchmarks, the learning efficiency of the proposed approach surpasses that using full-bit, semi-supervised supervision.
  arXiv  Detail & Related papers  (2023-11-26T07:39:00Z)
• Continual Learning in Open-vocabulary Classification with Complementary Memory Systems [19.337633598158778]
  We introduce a method for flexible and efficient continual learning in open-vocabulary image classification. We combine predictions from a CLIP zero-shot model and the exemplar-based model, using the zero-shot estimated probability that a sample's class is within the exemplar classes. We also propose a "tree probe" method, an adaption of lazy learning principles, which enables fast learning from new examples with competitive accuracy to batch-trained linear models.
  arXiv  Detail & Related papers  (2023-07-04T01:47:34Z)
• Deep Active Learning with Contrastive Learning Under Realistic Data Pool Assumptions [2.578242050187029]
  Active learning aims to identify the most informative data from an unlabeled data pool that enables a model to reach the desired accuracy rapidly. Most existing active learning methods have been evaluated in an ideal setting where only samples relevant to the target task exist in an unlabeled data pool. We introduce new active learning benchmarks that include ambiguous, task-irrelevant out-of-distribution as well as in-distribution samples.
  arXiv  Detail & Related papers  (2023-03-25T10:46:10Z)
• Intra-class Adaptive Augmentation with Neighbor Correction for Deep Metric Learning [99.14132861655223]
  We propose a novel intra-class adaptive augmentation (IAA) framework for deep metric learning. We reasonably estimate intra-class variations for every class and generate adaptive synthetic samples to support hard samples mining. Our method significantly improves and outperforms the state-of-the-art methods on retrieval performances by 3%-6%.
  arXiv  Detail & Related papers  (2022-11-29T14:52:38Z)
• Class-Incremental Learning with Strong Pre-trained Models [97.84755144148535]
  Class-incremental learning (CIL) has been widely studied under the setting of starting from a small number of classes (base classes) We explore an understudied real-world setting of CIL that starts with a strong model pre-trained on a large number of base classes. Our proposed method is robust and generalizes to all analyzed CIL settings.
  arXiv  Detail & Related papers  (2022-04-07T17:58:07Z)
• Optimizing Active Learning for Low Annotation Budgets [6.753808772846254]
  In deep learning, active learning is usually implemented as an iterative process in which successive deep models are updated via fine tuning. We tackle this issue by using an approach inspired by transfer learning. We introduce a novel acquisition function which exploits the iterative nature of AL process to select samples in a more robust fashion.
  arXiv  Detail & Related papers  (2022-01-18T18:53:10Z)
• Active Learning at the ImageNet Scale [43.595076693347835]
  In this work, we study a combination of active learning (AL) and pretraining (SSP) on ImageNet. We find that performance on small toy datasets is not representative of performance on ImageNet due to the class imbalanced samples selected by an active learner. We propose Balanced Selection (BASE), a simple, scalable AL algorithm that outperforms random sampling consistently.
  arXiv  Detail & Related papers  (2021-11-25T02:48:51Z)
• Improving Contrastive Learning on Imbalanced Seed Data via Open-World Sampling [96.8742582581744]
  We present an open-world unlabeled data sampling framework called Model-Aware K-center (MAK) MAK follows three simple principles: tailness, proximity, and diversity. We demonstrate that MAK can consistently improve both the overall representation quality and the class balancedness of the learned features.
  arXiv  Detail & Related papers  (2021-11-01T15:09:41Z)
• Prototypical Classifier for Robust Class-Imbalanced Learning [64.96088324684683]
  We propose textitPrototypical, which does not require fitting additional parameters given the embedding network. Prototypical produces balanced and comparable predictions for all classes even though the training set is class-imbalanced. We test our method on CIFAR-10LT, CIFAR-100LT and Webvision datasets, observing that Prototypical obtains substaintial improvements compared with state of the arts.
  arXiv  Detail & Related papers  (2021-10-22T01:55:01Z)

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.