RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening
Not on the map. Why?
Abstract (arXiv)
Enhancing the generalization capability of deep neural networks to unseen domains is crucial for safety-critical applications in the real world such as autonomous driving. To address this issue, this paper proposes a novel instance selective whitening loss to improve the robustness of the segmentation networks for unseen domains. Our approach disentangles the domain-specific style and domain-invariant content encoded in higher-order statistics (i.e., feature covariance) of the feature representations and selectively removes only the style information causing domain shift. As shown in Fig. 1, our method provides reasonable predictions for (a) low-illuminated, (b) rainy, and (c) unseen structures. These types of images are not included in the training dataset, where the baseline shows a significant performance drop, contrary to ours. Being simple yet effective, our approach improves the robustness of various backbone networks without additional computational cost. We conduct extensive experiments in urban-scene segmentation and show the superiority of our approach to existing work. Our code is available at https://github.com/shachoi/RobustNet.
Key facts. Cited by 213 papers in the map (data through 7 Oct 2026). Builds on 56 of its 70 references that are in the map. First posted on arXiv 29 Mar 2021.
Builds on
56 of 70 references.
References · 56
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 6,979
- 2014Fully Convolutional Networks for Semantic Segmentationcited by 4,845
- 2018MobileNetV2: Inverted Residuals and Linear Bottleneckscited by 4,773
- 2016The Cityscapes Dataset for Semantic Urban Scene Understandingcited by 4,427
- 2018Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentationcited by 3,210
- 2015Domain-Adversarial Training of Neural Networkscited by 3,023
- 2016Pyramid Scene Parsing Networkcited by 2,472
- 2017Rethinking Atrous Convolution for Semantic Image Segmentationcited by 2,154
- 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
- 2015SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentationcited by 1,483
38 more
- 2018BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learningcited by 1,282
- 2016Deep CORAL: Correlation Alignment for Deep Domain Adaptationcited by 1,194
- 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,187
- 2018ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Designcited by 1,132
- 2017CyCADA: Cycle-Consistent Adversarial Domain Adaptationcited by 1,079
- 2016Playing for Data: Ground Truth from Computer Gamescited by 816
- 2018Multimodal Unsupervised Image-to-Image Translationcited by 795
- 2017Learning to Generalize: Meta-Learning for Domain Generalizationcited by 762
- 2017Maximum Classifier Discrepancy for Unsupervised Domain Adaptationcited by 682
- 2018ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentationcited by 623
- 2013Domain Generalization via Invariant Feature Representationcited by 622
- 2018Learning to Adapt Structured Output Space for Semantic Segmentationcited by 584
- 2019Domain Generalization via Model-Agnostic Learning of Semantic Featurescited by 405
- 2018Two at Once: Enhancing Learning and Generalization Capacities via IBN-Netcited by 361
- 2017Universal Style Transfer via Feature Transformscited by 352
- 2017Unified Deep Supervised Domain Adaptation and Generalizationcited by 322
- 2018Diverse Image-to-Image Translation via Disentangled Representationscited by 296
- 2020Learning to Generate Novel Domains for Domain Generalizationcited by 296
- 2015Domain Generalization for Object Recognition with Multi-task Autoencoderscited by 253
- 2019Episodic Training for Domain Generalizationcited by 245
- 2019Domain Randomization and Pyramid Consistency: Simulation-to-Real Generalization without Accessing Target Domain Datacited by 245
- 2016FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptationcited by 242
- 2020Unsupervised Intra-domain Adaptation for Semantic Segmentation through Self-Supervisioncited by 198
- 2015ParseNet: Looking Wider to See Bettercited by 176
- 2018DLOW: Domain Flow for Adaptation and Generalizationcited by 176
- 2017Image to Image Translation for Domain Adaptationcited by 171
- 2019Learning to Optimize Domain Specific Normalization for Domain Generalizationcited by 160
- 2018Improving Semantic Segmentation via Video Propagation and Label Relaxationcited by 134
- 2018A Closed-form Solution to Photorealistic Image Stylizationcited by 133
- 2019Feature-Critic Networks for Heterogeneous Domain Generalizationcited by 130
- 2017Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenescited by 105
- 2019Switchable Whitening for Deep Representation Learningcited by 105
- 2018DCAN: Dual Channel-wise Alignment Networks for Unsupervised Scene Adaptationcited by 101
- 2017ROAD: Reality Oriented Adaptation for Semantic Segmentation of Urban Scenescited by 95
- 2019Iterative Normalization: Beyond Standardization towards Efficient Whiteningcited by 92
- 2018Decorrelated Batch Normalizationcited by 83
- 2020Cars Can't Fly up in the Sky: Improving Urban-Scene Segmentation via Height-driven Attention Networkscited by 70
- 2019Unsupervised Domain Adaptation using Feature-Whitening and Consensus Losscited by 67
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2021: 8; 2022: 42; 2023: 60; 2024: 40; 2025: 51; 2026: 12.
213 papers.
Sort:
By area:
- 2023Transformer-Based Visual Segmentation: A Surveycited by 124
- 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
- 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
- 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
- 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
- 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
- 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 82
- 2022Semantic-Aware Domain Generalized Segmentationcited by 78
- 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
- 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
- 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
- 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
38 more
- 2021Test-time Batch Statistics Calibration for Covariate Shiftcited by 50
- 2022Pin the Memory: Learning to Generalize Semantic Segmentationcited by 48
- 2022Revisiting Domain Generalized Stereo Matching Networks from a Feature Consistency Perspectivecited by 46
- 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Controlcited by 44
- 2021Source-Free Open Compound Domain Adaptation in Semantic Segmentationcited by 43
- 2023Instance-Aware Domain Generalization for Face Anti-Spoofingcited by 42
- 2021Feature Stylization and Domain-aware Contrastive Learning for Domain Generalizationcited by 40
- 2022ITSA: An Information-Theoretic Approach to Automatic Shortcut Avoidance and Domain Generalization in Stereo Matching Networkscited by 39
- 2023Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimizationcited by 39
- 2022PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalizationcited by 38
- 2023Progressive Random Convolutions for Single Domain Generalizationcited by 33
- 2023Collaborating Foundation Models for Domain Generalized Semantic Segmentationcited by 33
- 2022FIFO: Learning Fog-invariant Features for Foggy Scene Segmentationcited by 31
- 2023HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentationcited by 31
- 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentationcited by 30
- 2023Survey on Unsupervised Domain Adaptation for Semantic Segmentation for Visual Perception in Automated Drivingcited by 29
- 2023Learning Content-enhanced Mask Transformer for Domain Generalized Urban-Scene Segmentationcited by 29
- 2024Improving Single Domain-Generalized Object Detection: A Focus on Diversification and Alignmentcited by 29
- 2024Unbiased Faster R-CNN for Single-source Domain Generalized Object Detectioncited by 29
- 2023SRCD: Semantic Reasoning with Compound Domains for Single-Domain Generalized Object Detectioncited by 28
- 2023A Simple Recipe for Language-guided Domain Generalized Segmentationcited by 27
- 2023Generalization by Adaptation: Diffusion-Based Domain Extension for Domain-Generalized Semantic Segmentationcited by 27
- 2023Semantic Image Segmentation: Two Decades of Researchcited by 26
- 2023Domain Adaptive and Generalizable Network Architectures and Training Strategies for Semantic Image Segmentationcited by 26
- 2021WEDGE: Web-Image Assisted Domain Generalization for Semantic Segmentationcited by 25
- 2024BECoTTA: Input-dependent Online Blending of Experts for Continual Test-time Adaptationcited by 25
- 2024Prompt-Driven Dynamic Object-Centric Learning for Single Domain Generalizationcited by 24
- 2024UniMix: Towards Domain Adaptive and Generalizable LiDAR Semantic Segmentation in Adverse Weathercited by 24
- 2023Texture Learning Domain Randomization for Domain Generalized Segmentationcited by 23
- 2024Rethinking Multi-domain Generalization with A General Learning Objectivecited by 23
- 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentationcited by 23
- 2022Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalizationcited by 22
- 2024SoMA: Singular Value Decomposed Minor Components Adaptation for Domain Generalizable Representation Learningcited by 22
- 2022CAFA: Class-Aware Feature Alignment for Test-Time Adaptationcited by 21
- 2022Cross-Domain Ensemble Distillation for Domain Generalizationcited by 21
- 2023Object-Aware Domain Generalization for Object Detectioncited by 21
- 2024Learning Spectral-Decomposed Tokens for Domain Generalized Semantic Segmentationcited by 21
- 2021MVDG: A Unified Multi-view Framework for Domain Generalizationcited by 20
50 most cited of 213 All 213 (JSON)
- 2026Hierarchical Prompt Injector for Domain Generalization Segmentation5 Sep 2026
- 2026Generative Semantic Segmentation via an Observable Semantic-Image Interface and Hierarchical Generator Evidence Alignment12 Aug 2026
- 2026LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation9 Aug 2026
- 2026Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection8 Jul 2026
- 2026A Sliced-Wasserstein Framework on Correlation Matrices for EEG Decoding4 Jun 2026
- 2026Multiple Domain Generalization Using Category Information Independent of Domain Differences8 Apr 2026
- 2026Rethinking Representations for Cross-Domain Infrared Small Target Detection: A Generalizable Perspective from the Frequency Domain2 Apr 2026
- 2026RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation30 Mar 2026
- 2026CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection17 Mar 2026
- 2026Local Precise Refinement: A Dual-Gated Mixture-of-Experts for Enhancing Foundation Model Generalization against Spectral Shifts8 Mar 2026
- 2026Time2General: Learning Spatiotemporal Invariant Representations for Domain-Generalization Video Semantic Segmentation10 Feb 2026
- 2026One-Shot Crowd Counting With Density Guidance For Scene Adaptation8 Feb 2026
38 more
- 2025Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentation18 Dec 2025
- 2025Test-Time Modification: Inverse Domain Transformation for Robust Perception15 Dec 2025
- 2025Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation3 Dec 2025
- 2025SAGE: Style-Adaptive Generalization for Privacy-Constrained Semantic Segmentation Across Domains2 Dec 2025
- 2025RobustSurg: Tackling domain generalisation for out-of-distribution surgical scene segmentation1 Dec 2025
- 2025Semantic-aware Random Convolution and Source Matching for Domain Generalization in Medical Image Segmentation1 Dec 2025
- 2025Do We Need Perfect Data? Leveraging Noise for Domain Generalized Segmentation28 Nov 2025
- 2025AngioDG: Interpretable Channel-informed Feature-modulated Single-source Domain Generalization for Coronary Vessel Segmentation in X-ray Angiography21 Nov 2025
- 2025Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts22 Oct 2025
- 2025Domain Generalization for Semantic Segmentation: A Survey3 Oct 2025
- 2025ConstStyle: Robust Domain Generalization with Unified Style Transformation7 Sep 2025
- 2025Target-Oriented Single Domain Generalization30 Aug 2025
- 2025IELDG: Suppressing Domain-Specific Noise with Inverse Evolution Layers for Domain Generalized Semantic Segmentation27 Aug 2025
- 2025Bridging Clear and Adverse Driving Conditions19 Aug 2025
- 2025Multi-Granularity Feature Calibration via VFM for Domain Generalized Semantic Segmentation5 Aug 2025
- 2025Rein++: Efficient Generalization and Adaptation for Semantic Segmentation with Vision Foundation Models3 Aug 2025
- 2025Set Pivot Learning: Redefining Generalized Segmentation with Vision Foundation Models3 Aug 2025
- 2025Details Matter for Indoor Open-vocabulary 3D Instance Segmentation30 Jul 2025
- 2025Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation28 Jul 2025
- 2025Prototypical Progressive Alignment and Reweighting for Generalizable Semantic Segmentation16 Jul 2025
- 2025Bridging Domain Generalization to Multimodal Domain Generalization via Unified Representations4 Jul 2025
- 2025Continual Adaptation: Environment-Conditional Parameter Generation for Object Detection in Dynamic Scenarios30 Jun 2025
- 2025Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability26 Jun 2025
- 2025Orthogonal Projection Subspace to Aggregate Online Prior-knowledge for Continual Test-time Adaptation23 Jun 2025
- 2025Towards Conditional Feature Alignment for Cross-Domain Counting20 Jun 2025
- 2025ConStyX: Content Style Augmentation for Generalizable Medical Image Segmentation12 Jun 2025
- 2025Leveraging Depth and Language for Open-Vocabulary Domain-Generalized Semantic Segmentation11 Jun 2025
- 2025Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World7 Jun 2025
- 2025Single Domain Generalization for Few-Shot Counting via Universal Representation Matching22 May 2025
- 2025Language-Driven Dual Style Mixing for Single-Domain Generalized Object Detection12 May 2025
- 2025Depth-Sensitive Soft Suppression with RGB-D Inter-Modal Stylization Flow for Domain Generalization Semantic Segmentation11 May 2025
- 2025Style-Adaptive Detection Transformer for Single-Source Domain Generalized Object Detection29 Apr 2025
- 2025DG-DETR: Toward Domain Generalized Detection Transformer28 Apr 2025
- 2025Boosting Single-domain Generalized Object Detection via Vision-Language Knowledge Interaction27 Apr 2025
- 2025What is the Added Value of UDA in the VFM Era?25 Apr 2025
- 2025Stronger, Steadier & Superior: Geometric Consistency in Depth VFM Forges Domain Generalized Semantic Segmentation17 Apr 2025
- 2025Domain Generalization through Attenuation of Domain-Specific Information9 Apr 2025
- 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation4 Apr 2025
50 newest of 213 All 213 (JSON)
- 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Controlcited by 44
- 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentationcited by 30
- 2025Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detectioncited by 6
- 2024Diffusion Features to Bridge Domain Gap for Semantic Segmentationcited by 5
- 2024Syn2Real Domain Generalization for Underwater Mine-like Object Detection Using Side-Scan Sonarcited by 4
- 2025Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentationcited by 3
- 2025Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferabilitycited by 2
- 2025Exploring Probabilistic Modeling Beyond Domain Generalization for Semantic Segmentation28 Jul 2025
- 2025Boosting Domain Generalized and Adaptive Detection with Diffusion Models: Fitness, Generalization, and Transferability26 Jun 2025
- 2025Generalized Diffusion Detector: Mining Robust Features from Diffusion Models for Domain-Generalized Detection3 Mar 2025
- 2024Syn2Real Domain Generalization for Underwater Mine-like Object Detection Using Side-Scan Sonar16 Oct 2024
- 2024Diffusion Features to Bridge Domain Gap for Semantic Segmentation2 Jun 2024
- 2023DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control5 Dec 2023
- 2023Prompting Diffusion Representations for Cross-Domain Semantic Segmentation5 Jul 2023
- 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentationcited by 23
- 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learningcited by 20
- 2024Textual Query-Driven Mask Transformer for Domain Generalized Segmentationcited by 20
- 2025Details Matter for Indoor Open-vocabulary 3D Instance Segmentationcited by 8
- 2025Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentationcited by 4
- 2025Exploiting Domain Properties in Language-Driven Domain Generalization for Semantic Segmentation3 Dec 2025
- 2025Details Matter for Indoor Open-vocabulary 3D Instance Segmentation30 Jul 2025
- 2025Mamba as a Bridge: Where Vision Foundation Models Meet Vision Language Models for Domain-Generalized Semantic Segmentation4 Apr 2025
- 2024Textual Query-Driven Mask Transformer for Domain Generalized Segmentation12 Jul 2024
- 2023Strong but simple: A Baseline for Domain Generalized Dense Perception by CLIP-based Transfer Learning4 Dec 2023
- 2023Transformer-Based Visual Segmentation: A Surveycited by 124
- 2023EcoTTA: Memory-Efficient Continual Test-time Adaptation via Self-distilled Regularizationcited by 123
- 2022Uncertainty Modeling for Out-of-Distribution Generalizationcited by 122
- 2023TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptationcited by 101
- 2022Style-Hallucinated Dual Consistency Learning for Domain Generalized Semantic Segmentationcited by 88
- 2023CLIP the Gap: A Single Domain Generalization Approach for Object Detectioncited by 87
- 2023Stronger, Fewer, & Superior: Harnessing Vision Foundation Models for Domain Generalized Semantic Segmentationcited by 82
- 2022Semantic-Aware Domain Generalized Segmentationcited by 78
- 2021Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentationcited by 77
- 2022WildNet: Learning Domain Generalized Semantic Segmentation from the Wildcited by 75
- 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
- 2022Improving Test-Time Adaptation via Shift-agnostic Weight Regularization and Nearest Source Prototypescited by 67
12 most cited of 199 All 199 (JSON)
- 2026Hierarchical Prompt Injector for Domain Generalization Segmentation5 Sep 2026
- 2026Generative Semantic Segmentation via an Observable Semantic-Image Interface and Hierarchical Generator Evidence Alignment12 Aug 2026
- 2026LASA: Language-and-Source-Anchored Alignment for Domain Generalized Semantic Segmentation9 Aug 2026
- 2026Prototype-Anchored Generalized Manifold Regression for Unknown-Domain Object Detection8 Jul 2026
- 2026A Sliced-Wasserstein Framework on Correlation Matrices for EEG Decoding4 Jun 2026
- 2026Multiple Domain Generalization Using Category Information Independent of Domain Differences8 Apr 2026
- 2026Rethinking Representations for Cross-Domain Infrared Small Target Detection: A Generalizable Perspective from the Frequency Domain2 Apr 2026
- 2026RecycleLoRA: Rank-Revealing QR-Based Dual-LoRA Subspace Adaptation for Domain Generalized Semantic Segmentation30 Mar 2026
- 2026CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection17 Mar 2026
- 2026Time2General: Learning Spatiotemporal Invariant Representations for Domain-Generalization Video Semantic Segmentation10 Feb 2026
- 2026One-Shot Crowd Counting With Density Guidance For Scene Adaptation8 Feb 2026
- 2025Causal-Tune: Mining Causal Factors from Vision Foundation Models for Domain Generalized Semantic Segmentation18 Dec 2025
12 newest of 199 All 199 (JSON)