Universal Incremental Learning: Mitigating Confusion from Inter- and Intra-task Distribution Randomness

• URL: http://arxiv.org/abs/2503.07035v1
• Date: Mon, 10 Mar 2025 08:20:55 GMT
• Title: Universal Incremental Learning: Mitigating Confusion from Inter- and Intra-task Distribution Randomness
• Authors: Sheng Luo, Yi Zhou, Tao Zhou,
• Abstract summary: Incremental learning aims to overcome forgetting of previous tasks while learning new ones.<n>Existing IL methods make strong assumptions that the incoming task type will either only increase new classes or domains.<n>We propose a simple yet effective framework for UIL, named $textbfMiCo$.
• Score: 11.082975265204487
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Incremental learning (IL) aims to overcome catastrophic forgetting of previous tasks while learning new ones. Existing IL methods make strong assumptions that the incoming task type will either only increases new classes or domains (i.e. Class IL, Domain IL), or increase by a static scale in a class- and domain-agnostic manner (i.e. Versatile IL (VIL)), which greatly limit their applicability in the unpredictable and dynamic wild. In this work, we investigate $\textbf{Universal Incremental Learning (UIL)}$, where a model neither knows which new classes or domains will increase along sequential tasks, nor the scale of the increments within each task. This uncertainty prevents the model from confidently learning knowledge from all task distributions and symmetrically focusing on the diverse knowledge within each task distribution. Consequently, UIL presents a more general and realistic IL scenario, making the model face confusion arising from inter-task and intra-task distribution randomness. To $\textbf{Mi}$tigate both $\textbf{Co}$nfusion, we propose a simple yet effective framework for UIL, named $\textbf{MiCo}$. At the inter-task distribution level, we employ a multi-objective learning scheme to enforce accurate and deterministic predictions, and its effectiveness is further enhanced by a direction recalibration module that reduces conflicting gradients. Moreover, at the intra-task distribution level, we introduce a magnitude recalibration module to alleviate asymmetrical optimization towards imbalanced class distribution. Extensive experiments on three benchmarks demonstrate the effectiveness of our method, outperforming existing state-of-the-art methods in both the UIL scenario and the VIL scenario. Our code will be available at $\href{https://github.com/rolsheng/UIL}{here}$.

Related papers

• Navigating Semantic Drift in Task-Agnostic Class-Incremental Learning [51.177789437682954]
  Class-incremental learning (CIL) seeks to enable a model to sequentially learn new classes while retaining knowledge of previously learned ones.<n> Balancing flexibility and stability remains a significant challenge, particularly when the task ID is unknown.<n>We propose a novel semantic drift calibration method that incorporates mean shift compensation and covariance calibration.
  arXiv  Detail & Related papers  (2025-02-11T13:57:30Z)
• Versatile Incremental Learning: Towards Class and Domain-Agnostic Incremental Learning [16.318126586825734]
  Incremental Learning (IL) aims to accumulate knowledge from sequential input tasks. We consider a more challenging and realistic but under-explored IL scenario, named Versatile Incremental Learning (VIL) We propose a simple yet effective IL framework, named Incremental with Shift cONtrol (ICON)
  arXiv  Detail & Related papers  (2024-09-17T07:44:28Z)
• Task-Distributionally Robust Data-Free Meta-Learning [99.56612787882334]
  Data-Free Meta-Learning (DFML) aims to efficiently learn new tasks by leveraging multiple pre-trained models without requiring their original training data. For the first time, we reveal two major challenges hindering their practical deployments: Task-Distribution Shift ( TDS) and Task-Distribution Corruption (TDC)
  arXiv  Detail & Related papers  (2023-11-23T15:46:54Z)
• Improved Active Multi-Task Representation Learning via Lasso [44.607652031235716]
  In this paper, we show the dominance of the L1-regularized-relevance-based ($nu1$) strategy by giving a lower bound for the $nu2$-based strategy. We also characterize the potential of our $nu1$-based strategy in sample-cost-sensitive settings.
  arXiv  Detail & Related papers  (2023-06-05T03:08:29Z)
• Towards Understanding and Improving GFlowNet Training [71.85707593318297]
  We introduce an efficient evaluation strategy to compare the learned sampling distribution to the target reward distribution. We propose prioritized replay training of high-reward $x$, relative edge flow policy parametrization, and a novel guided trajectory balance objective.
  arXiv  Detail & Related papers  (2023-05-11T22:50:41Z)
• Multi-Level Contrastive Learning for Dense Prediction Task [59.591755258395594]
  We present Multi-Level Contrastive Learning for Dense Prediction Task (MCL), an efficient self-supervised method for learning region-level feature representation for dense prediction tasks. Our method is motivated by the three key factors in detection: localization, scale consistency and recognition. Our method consistently outperforms the recent state-of-the-art methods on various datasets with significant margins.
  arXiv  Detail & Related papers  (2023-04-04T17:59:04Z)
• Self-Supervised Learning by Estimating Twin Class Distributions [26.7828253129684]
  We present TWIST, a novel self-supervised representation learning method by classifying large-scale unlabeled datasets in an end-to-end way. We employ a siamese network terminated by a softmax operation to produce twin class distributions of two augmented images. Specifically, we minimize the entropy of the distribution for each sample to make the class prediction for each sample and maximize the entropy of the mean distribution to make the predictions of different samples diverse.
  arXiv  Detail & Related papers  (2021-10-14T14:39:39Z)
• Towards Accurate Knowledge Transfer via Target-awareness Representation Disentanglement [56.40587594647692]
  We propose a novel transfer learning algorithm, introducing the idea of Target-awareness REpresentation Disentanglement (TRED) TRED disentangles the relevant knowledge with respect to the target task from the original source model and used as a regularizer during fine-tuning the target model. Experiments on various real world datasets show that our method stably improves the standard fine-tuning by more than 2% in average.
  arXiv  Detail & Related papers  (2020-10-16T17:45:08Z)
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation [63.75774438196315]
  Unsupervised domain adaptation (UDA) aims to adapt existing models of the source domain to a new target domain with only unlabeled data. Most existing methods suffer from noticeable negative transfer resulting from either the error-prone discriminator network or the unreasonable teacher model. We propose an uncertainty-aware consistency regularization method for cross-domain semantic segmentation.
  arXiv  Detail & Related papers  (2020-04-19T15:30:26Z)

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.