Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning

• URL: http://arxiv.org/abs/2605.08839v1
• Date: Sat, 09 May 2026 09:49:13 GMT
• Title: Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning
• Abstract summary: Class-Incremental Learning (CIL) requires a learning system to learn new classes while retaining previously learned knowledge.<n>In real-world scenarios such as autonomous driving, a system trained on urban roads in sunny weather may later need to operate in rural or highway environments.<n>We propose a unified framework to address domain shift and catastrophic forgetting simultaneously.
• Score: 83.67663266193308
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Class-Incremental Learning (CIL) requires a learning system to learn new classes while retaining previously learned knowledge. However, in real-world scenarios such as autonomous driving, a system trained on urban roads in sunny weather may later need to operate in rural or highway environments with different traffic patterns and weather conditions. This requires the model not only to overcome catastrophic forgetting, but also to effectively handle domain shifts. In this paper, we propose CrOss-sample Relational Fusion (CORF), a unified framework to address domain shift and catastrophic forgetting simultaneously. To enhance generalizability, we perform selective refinement of training samples by leveraging spatial contribution maps to highlight semantically informative regions. Furthermore, we incorporate predictive confidence to adaptively weigh samples, thereby facilitating the learning of domain-agnostic representations. To alleviate forgetting, we propose a cascaded distillation framework that captures cross-sample relational dependencies across multiple feature hierarchies, enabling multi-grained knowledge transfer from previous tasks. CORF can be seamlessly integrated into existing CIL algorithms to enhance their generalizability, achieving competitive performance across various benchmark datasets. Code is available at https://github.com/LAMDA-CL/TMM26-CORF .

Related papers

• Adaptive Learning Strategies for AoA-Based Outdoor Localization: A Comprehensive Framework [4.445694723459059]
  We propose an adaptive framework for AoA-based localization that consists of two alternative learning strategies.<n>The proposed framework is evaluated on a real, massive multiple input multiple output (mMIMO) dataset.<n>Results show that highly accurate robust localization can be achieved incrementally during network operation by exploiting online learning.
  arXiv  Detail & Related papers  (2026-05-06T15:51:34Z)
• Enhancing Gradient Inversion Attacks in Federated Learning via Hierarchical Feature Optimization [56.95448807869383]
  Federated Learning (FL) has emerged as a compelling paradigm for privacy-preserving distributed machine learning.<n>Recent studies find that the gradients exchanged in the FL system are also vulnerable to privacy leakage.<n>We propose textbfGradient textbfInversion over textbfFeature textbfDomains (GIFD)
  arXiv  Detail & Related papers  (2026-04-01T14:32:15Z)
• Knowledge-Aware Evolution for Streaming Federated Continual Learning with Category Overlap and without Task Identifiers [0.0]
  Federated Continual Learning (FCL) leverages inter-client collaboration to balance new knowledge acquisition and prior knowledge retention in non-stationary data.<n>Existing batch-based FCL methods lack adaptability to streaming scenarios featuring category overlap between old and new data and absent task identifiers.<n>We propose streaming federated continual learning setting: per federated learning (FL) round, clients process streaming data with disjoint samples and potentially overlapping categories without task identifiers.<n>Experiments across multiple scenarios and regret analysis demonstrate the effectiveness of FedKACE.
  arXiv  Detail & Related papers  (2026-01-27T16:50:48Z)
• RECALL: REpresentation-aligned Catastrophic-forgetting ALLeviation via Hierarchical Model Merging [33.22889542330089]
  Internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge.<n>We propose RECALL, a representation-aware model merging framework for continual learning without access to historical data.
  arXiv  Detail & Related papers  (2025-10-23T12:17:37Z)
• A Spatiotemporal Correspondence Approach to Unsupervised LiDAR Segmentation with Traffic Applications [16.260518238832887]
  Key idea is to leverage the nature of a dynamic point cloud sequence and introduce drastically stronger scenarios. We alternate between optimizing semantic into groups and clustering using point-wisetemporal labels. Our method can learn discriminative features in an unsupervised learning fashion.
  arXiv  Detail & Related papers  (2023-08-23T21:32:46Z)
• Beyond Transfer Learning: Co-finetuning for Action Localisation [64.07196901012153]
  We propose co-finetuning -- simultaneously training a single model on multiple upstream'' and downstream'' tasks. We demonstrate that co-finetuning outperforms traditional transfer learning when using the same total amount of data. We also show how we can easily extend our approach to multiple upstream'' datasets to further improve performance.
  arXiv  Detail & Related papers  (2022-07-08T10:25:47Z)
• Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS [10.087704332539161]
  We introduce a federated learning framework coping with Hierarchical Heterogeneity (H2-Fed) The framework exploits data from connected public traffic agents in vehicular networks without affecting user data privacy.
  arXiv  Detail & Related papers  (2022-04-01T05:33:54Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Edge-assisted Democratized Learning Towards Federated Analytics [67.44078999945722]
  We show the hierarchical learning structure of the proposed edge-assisted democratized learning mechanism, namely Edge-DemLearn. We also validate Edge-DemLearn as a flexible model training mechanism to build a distributed control and aggregation methodology in regions.
  arXiv  Detail & Related papers  (2020-12-01T11:46:03Z)
• Learning to Combine: Knowledge Aggregation for Multi-Source Domain Adaptation [56.694330303488435]
  We propose a Learning to Combine for Multi-Source Domain Adaptation (LtC-MSDA) framework. In the nutshell, a knowledge graph is constructed on the prototypes of various domains to realize the information propagation among semantically adjacent representations. Our approach outperforms existing methods with a remarkable margin.
  arXiv  Detail & Related papers  (2020-07-17T07:52:44Z)

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.