Prior-based Domain Adaptive Object Detection for Hazy and Rainy Conditions

TL;DR

This paper introduces an unsupervised domain adaptation framework that uses weather-specific priors and feature recovery blocks to improve object detection in hazy and rainy conditions, outperforming existing methods.

Contribution

It proposes a novel prior-adversarial loss and residual feature recovery blocks for effective adaptation to adverse weather in object detection.

Findings

Significant improvement in detection accuracy on hazy and rainy datasets.

Effective reduction of weather-specific information in feature representations.

Outperforms baseline methods on multiple challenging datasets.

Abstract

Adverse weather conditions such as haze and rain corrupt the quality of captured images, which cause detection networks trained on clean images to perform poorly on these images. To address this issue, we propose an unsupervised prior-based domain adversarial object detection framework for adapting the detectors to hazy and rainy conditions. In particular, we use weather-specific prior knowledge obtained using the principles of image formation to define a novel prior-adversarial loss. The prior-adversarial loss used to train the adaptation process aims to reduce the weather-specific information in the features, thereby mitigating the effects of weather on the detection performance. Additionally, we introduce a set of residual feature recovery blocks in the object detection pipeline to de-distort the feature space, resulting in further improvements. Evaluations performed on various datasets (Foggy-Cityscapes, Rainy-Cityscapes, RTTS and UFDD) for rainy and hazy conditions demonstrates the effectiveness of the proposed approach.