Multi-Target Domain Adaptation via Unsupervised Domain Classification for Weather Invariant Object Detection

TL;DR

This paper introduces an unsupervised domain classification approach to enable weather-invariant object detection across multiple weather conditions, improving robustness in autonomous driving scenarios.

Contribution

It presents a novel method for multi-target domain adaptation that does not require domain labels, enhancing object detection under diverse weather conditions.

Findings

Improved detection accuracy across foggy, rainy, and night conditions

Effective generalization to multiple weather domains without domain labels

Robust object detection demonstrated on Cityscapes and synthetic variants

Abstract

Object detection is an essential technique for autonomous driving. The performance of an object detector significantly degrades if the weather of the training images is different from that of test images. Domain adaptation can be used to address the domain shift problem so as to improve the robustness of an object detector. However, most existing domain adaptation methods either handle single target domain or require domain labels. We propose a novel unsupervised domain classification method which can be used to generalize single-target domain adaptation methods to multi-target domains, and design a weather-invariant object detector training framework based on it. We conduct the experiments on Cityscapes dataset and its synthetic variants, i.e. foggy, rainy, and night. The experimental results show that the object detector trained by our proposed method realizes robust object detection under different weather conditions.