Log In Sign Up

Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss

by   Dongseok Shim, et al.

Deep neural networks have been widely studied in autonomous driving applications such as semantic segmentation or depth estimation. However, training a neural network in a supervised manner requires a large amount of annotated labels which are expensive and time-consuming to collect. Recent studies leverage synthetic data collected from a virtual environment which are much easier to acquire and more accurate compared to data from the real world, but they usually suffer from poor generalization due to the inherent domain shift problem. In this paper, we propose a Domain-Agnostic Contrastive Learning (DACL) which is a two-stage unsupervised domain adaptation framework with cyclic adversarial training and contrastive loss. DACL leads the neural network to learn domain-agnostic representation to overcome performance degradation when there exists a difference between training and test data distribution. Our proposed approach achieves better performance in the monocular depth estimation task compared to previous state-of-the-art methods and also shows effectiveness in the semantic segmentation task.


page 1

page 3

page 4

page 6


Plugging Self-Supervised Monocular Depth into Unsupervised Domain Adaptation for Semantic Segmentation

Although recent semantic segmentation methods have made remarkable progr...

Learning a Geometric Representation for Data-Efficient Depth Estimation via Gradient Field and Contrastive Loss

Estimating a depth map from a single RGB image has been investigated wid...

DESC: Domain Adaptation for Depth Estimation via Semantic Consistency

Accurate real depth annotations are difficult to acquire, needing the us...

Video Class Agnostic Segmentation with Contrastive Learning for Autonomous Driving

Semantic segmentation in autonomous driving predominantly focuses on lea...

Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks

Monocular Depth Estimation (MDE) is a critical component in applications...

False Negative Reduction in Semantic Segmentation under Domain Shift using Depth Estimation

State-of-the-art deep neural networks demonstrate outstanding performanc...

Improving Online Performance Prediction for Semantic Segmentation

In this work we address the task of observing the performance of a seman...

Code Repositories


Official PyTorch implementation of the paper "Learning a Domain-Agnostic Visual Representation for Autonomous Driving via Contrastive Loss"

view repo