Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

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

About

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.

Vishwanath A. Sindagi, Poojan Oza, Rajeev Yasarla, Vishal M. Patel• 2019

Related benchmarks

TaskDatasetResultRank
Object DetectionFoggy Cityscapes (test)
AP (Person)36.4
161
Object DetectionFoggy Cityscapes (val)
mAP39.3
67
Showing 2 of 2 rows

Other info

Follow for update