mlsanityData to 14 Oct 2026

Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentation

arXiv 2407.18568 ↗First posted 26 Jul 2024cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

The rapid development of Vision Foundation Model (VFM) brings inherent out-domain generalization for a variety of down-stream tasks. Among them, domain generalized semantic segmentation (DGSS) holds unique challenges as the cross-domain images share common pixel-wise content information but vary greatly in terms of the style. In this paper, we present a novel Spectral-dEcomposed Token (SET) learning framework to advance the frontier. Delving into further than existing fine-tuning token & frozen backbone paradigm, the proposed SET especially focuses on the way learning style-invariant features from these learnable tokens. Particularly, the frozen VFM features are first decomposed into the phase and amplitude components in the frequency space, which mainly contain the information of content and style, respectively, and then separately processed by learnable tokens for task-specific information extraction. After the decomposition, style variation primarily impacts the token-based feature enhancement within the amplitude branch. To address this issue, we further develop an attention optimization method to bridge the gap between style-affected representation and static tokens during inference. Extensive cross-domain experiments show its state-of-the-art performance.

Key facts. Cited by 22 papers in the map (data through 14 Oct 2026). Builds on 44 of its 69 references that are in the map. First posted on arXiv 26 Jul 2024.

Builds on

44 of 69 references.

References · 44

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,380
  3. 2023Segment Anythingcited by 8,234
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  5. 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,444
  6. 2021Zero-Shot Text-to-Image Generationcited by 4,288
  7. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  8. 2016Playing for Data: Ground Truth from Computer Gamescited by 818
  9. 2022AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognitioncited by 719
  10. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 691
  11. 2020FDA: Fourier Domain Adaptation for Semantic Segmentationcited by 541
  12. 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 364
32 more
  1. 2021A Fourier-based Framework for Domain Generalizationcited by 290
  2. 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 246
  3. 2021RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whiteningcited by 215
  4. 2021SelfReg: Self-supervised Contrastive Regularization for Domain Generalizationcited by 189
  5. 2021FSDR: Frequency Space Domain Randomization for Domain Generalizationcited by 164
  6. 2023Segment Anything Is Not Always Perfect: An Investigation of SAM on Different Real-world Applicationscited by 121
  7. 2019Switchable Whitening for Deep Representation Learningcited by 106
  8. 2019Iterative Normalization: Beyond Standardization towards Efficient Whiteningcited by 92
  9. 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 89
  10. 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 83
  11. 2018Batch-Instance Normalization for Adaptively Style-Invariant Neural Networkscited by 78
  12. 2020Meta Batch-Instance Normalization for Generalizable Person Re-Identificationcited by 77
  13. 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 76
  14. 2021Amplitude-Phase Recombination: Rethinking Robustness of Convolutional Neural Networks in Frequency Domaincited by 71
  15. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 70
  16. 2020Adversarial Style Mining for One-Shot Unsupervised Domain Adaptationcited by 64
  17. 2020Batch Normalization Embeddings for Deep Domain Generalizationcited by 57
  18. 2021Global and Local Texture Randomization for Synthetic-to-Real Semantic Segmentationcited by 57
  19. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  20. 2023Rethinking Domain Generalization for Face Anti-spoofing: Separability and Alignmentcited by 48
  21. 2020Self-Supervised Learning Across Domainscited by 44
  22. 2023Meta-causal Learning for Single Domain Generalizationcited by 43
  23. 2023HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentationcited by 32
  24. 2023Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentationcited by 30
  25. 2023Decompose, Adjust, Compose: Effective Normalization by Playing with Frequency for Domain Generalizationcited by 26
  26. 2022Test-time Fourier Style Calibration for Domain Generalizationcited by 25
  27. 2023MADG: Margin-based Adversarial Learning for Domain Generalizationcited by 22
  28. 2022Domain Generalization via Frequency-domain-based Feature Disentanglement and Interactioncited by 21
  29. 2022Intra-Source Style Augmentation for Improved Domain Generalizationcited by 17
  30. 2023Unsupervised Domain Adaptation for Semantic Segmentation with Pseudo Label Self-Refinementcited by 16
  31. 2023AdvST: Revisiting Data Augmentations for Single Domain Generalizationcited by 16
  32. 2023Foresee What You Will Learn: Data Augmentation for Domain Generalization in Non-stationary Environmentcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 14; 2026: 5.

22 papers.

Sort:

By area:

  1. 2024SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learningcited by 24
  2. 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentationcited by 24
  3. 2025FisherTune: Fisher-Guided Robust Tuning of Vision Foundation Models for Domain Generalized Segmentationcited by 16
  4. 2024Multi-source Domain Adaptation for Panoramic Semantic Segmentationcited by 8
  5. 2025SSH: Sparse Spectrum Adaptation via Discrete Hartley Transformationcited by 7
  6. 2025Learning Fine-grained Domain Generalization via Hyperbolic State Space Hallucinationcited by 7
  7. 2024BiDoRA: Bi-level Optimization-Based Weight-Decomposed Low-Rank Adaptationcited by 4
  8. 2025ER-LoRA: Effective-Rank Guided Adaptation for Weather-Generalized Depth Estimationcited by 4
  9. 2026Open-Vocabulary Domain Generalization in Urban-Scene Segmentationcited by 4
  10. 2025Generalizable Multispectral Land Cover Classification via Frequency-Aware Mixture of Low-Rank Token Expertscited by 3
  11. 2025Diversity Covariance-Aware Prompt Learning for Vision-Language Modelscited by 2
  12. 2025Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Modelscited by 2
10 more
  1. 2025Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 2
  2. 2025DGFamba: Learning Flow Factorized State Space for Visual Domain Generalizationcited by 1
  3. 2025SS-DC: Spatial-Spectral Decoupling and Coupling Across Visible-Infrared Gap for Domain Adaptive Object Detectioncited by 1
  4. 2026Local Precise Refinement: A Dual-Gated Mixture-of-Experts for Enhancing Foundation Model Generalization against Spectral Shiftscited by 1
  5. 2025Multi-Granularity Feature Calibration via VFM for Domain Generalized Semantic Segmentationcited by 0
  6. 2025Domain Generalization for Semantic Segmentation: A Surveycited by 0
  7. 2025SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domainscited by 0
  8. 2026RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentationcited by 0
  9. 2026Hierarchical Prompt Injector for Domain Generalization Segmentationcited by 0
  10. 2026Sparse All-Layer Connector for Domain Generalised Semantic Segmentationcited by 0