• Home
  • Search
  • Diverse Target and Contribution Scheduling for Domain Generalization.
  • Cite Icon2
  • https://doi.org/10.1109/tip.2025.3581012Copy DOI Icon

Diverse Target and Contribution Scheduling for Domain Generalization.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Generalization under distribution shifts has been a great challenge in computer vision. The prevailing practice of directly employing the one-hot labels as the training targets in domain generalization (DG) can lead to gradient conflicts, making it insufficient for capturing the intrinsic class characteristics and hard to increase the intra-class variation. Besides, existing methods in DG mostly overlook the distinct contributions of source (seen) domains, resulting in uneven learning from these domains. To address these issues, we first present a theoretical and empirical analysis on the existence of gradient conflicts in DG, unveiling the previously unexplored relationship between distribution shifts and gradient conflicts during optimization process. In this paper, we present a novel perspective of DG from the empirical source domain's risk, and propose a new paradigm for DG called Diverse Target and Contribution Scheduling (DTCS). DTCS comprises two innovative modules: Diverse Target Supervision (DTS) and Diverse Contribution Balance (DCB), with the aim of addressing the limitations associated with the common utilization of one-hot labels and equal contributions for source domains in DG. In specific, DTS employs distinct soft labels as training targets to account for various feature distributions across domains and thereby mitigates the gradient conflicts, and DCB dynamically balances the contributions of source domains by ensuring a fair decline in losses of different source domains. Extensive experiments with analysis on four benchmark datasets show that the proposed method achieves a competitive performance in comparison with the state-of-the-art approaches, demonstrating the effectiveness and advantages of the proposed DTCS. The source code will be available at https://github.com/longshaocong/DTCS.

Similar Papers
  • Dissertation
  • Citations1

Domain adaptation and generalization for visual recognition

  • Jan 01, 2017
  • Li Niu
  • PDF
  • Research Article
  • Citations5

Local domain generalization with low-rank constraint for EEG-based emotion recognition.

  • Nov 07, 2023
  • Frontiers in Neuroscience
  • Jianwen Tao +2
  • Research Article
  • Citations13

PLACE Dropout: A Progressive Layer-wise and Channel-wise Dropout for Domain Generalization

  • Oct 23, 2023
  • ACM Transactions on Multimedia Computing, Communications, and Applications
  • Jintao Guo +3
  • Research Article
  • Citations7

Adaptive Domain Generalization Via Online Disagreement Minimization.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Xin Zhang +1
  • Research Article
  • Citations1

Restoration towards decomposition: A simple approach for domain generalization

  • Jun 21, 2024
  • Information Sciences
  • Mengwei Li +2
  • Conference Article
  • Citations7

MCKD: Mutually Collaborative Knowledge Distillation For Federated Domain Adaptation And Generalization

  • Jun 04, 2023
  • Ziwei Niu +5
  • Conference Article
  • Citations61

Compound Domain Generalization via Meta-Knowledge Encoding

  • Jun 01, 2022
  • Chaoqi Chen +4
  • Research Article
  • Citations23

Generative Inference Network for Imbalanced Domain Generalization.

  • Jan 01, 2023
  • IEEE Transactions on Image Processing
  • Haifeng Xia +2
  • Research Article
  • Citations29

Better pseudo-label: Joint domain-aware label and dual-classifier for semi-supervised domain generalization

  • Aug 18, 2022
  • Pattern Recognition
  • Ruiqi Wang +3
  • Research Article
  • Citations33

Domain-augmented meta ensemble learning for mechanical fault diagnosis from heterogeneous source domains to unseen target domains

  • Sep 13, 2024
  • Expert Systems With Applications
  • Yiming Xiao +4
  • Research Article
  • Citations19

Mamba-Sea: A Mamba-Based Framework With Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation.

  • Sep 01, 2025
  • IEEE transactions on medical imaging
  • Zihan Cheng +6
  • Research Article
  • Citations90

Domain generalization on medical imaging classification using episodic training with task augmentation

  • Dec 24, 2021
  • Computers in Biology and Medicine
  • Chenxin Li +8
  • Conference Article
  • Citations1

Discrepancy-guided Channel Dropout for Domain Generalization

  • Oct 21, 2024
  • Seonggyeom Kim +3
  • Research Article
  • Citations24

Style and content separation network for remote sensing image cross-scene generalization

  • May 22, 2023
  • ISPRS Journal of Photogrammetry and Remote Sensing
  • Sihan Zhu +3
  • Research Article
  • Citations16

Semi-supervised domain generalization with evolving intermediate domain

  • Jan 12, 2024
  • Pattern Recognition
  • Luojun Lin +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.