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

03/29/2021
by   Sungha Choi, et al.
10

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.

READ FULL TEXT

page 1

page 2

page 8

page 12

page 15

page 16

page 17

page 18

research
08/20/2023

DomainDrop: Suppressing Domain-Sensitive Channels for Domain Generalization

Deep Neural Networks have exhibited considerable success in various visu...
research
01/30/2023

Adversarial Style Augmentation for Domain Generalization

It is well-known that the performance of well-trained deep neural networ...
research
04/12/2023

Instance-Aware Domain Generalization for Face Anti-Spoofing

Face anti-spoofing (FAS) based on domain generalization (DG) has been re...
research
02/27/2023

Learning to Generalize towards Unseen Domains via a Content-Aware Style Invariant Framework for Disease Detection from Chest X-rays

Performance degradation due to source domain mismatch is a longstanding ...
research
01/03/2021

Style Normalization and Restitution for DomainGeneralization and Adaptation

For many practical computer vision applications, the learned models usua...
research
04/04/2023

Randomized Adversarial Style Perturbations for Domain Generalization

We propose a novel domain generalization technique, referred to as Rando...
research
07/23/2021

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., ...

Please sign up or login with your details

Forgot password? Click here to reset