RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening

by   Sungha Choi, et al.

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


page 1

page 2

page 8

page 12

page 15

page 16

page 17

page 18


Style Normalization and Restitution for DomainGeneralization and Adaptation

For many practical computer vision applications, the learned models usua...

Achieving Domain Generalization in Underwater Object Detection by Image Stylization and Domain Mixup

The performance of existing underwater object detection methods degrades...

Revisiting Batch Normalization for Improving Corruption Robustness

Modern deep neural networks (DNN) have demonstrated remarkable success i...

Invariant Information Bottleneck for Domain Generalization

The main challenge for domain generalization (DG) is to overcome the pot...

Semantic-Aware Domain Generalized Segmentation

Deep models trained on source domain lack generalization when evaluated ...

Domain Intersection and Domain Difference

We present a method for recovering the shared content between two visual...

Standardized Max Logits: A Simple yet Effective Approach for Identifying Unexpected Road Obstacles in Urban-Scene Segmentation

Identifying unexpected objects on roads in semantic segmentation (e.g., ...

Code Repositories


Official PyTorch implementation of RobustNet (CVPR 2021 Oral)

view repo