TogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learning

TL;DR

TogetherNet is a unified framework that jointly learns image restoration and object detection to improve detection accuracy in adverse weather conditions, outperforming existing methods.

Contribution

It introduces a multi-task joint learning paradigm with a novel Dynamic Transformer Feature Enhancement module for better feature extraction.

Findings

Outperforms state-of-the-art detection methods in adverse weather scenarios.

Effective joint learning of restoration and detection improves detection accuracy.

Demonstrates robustness on synthetic and real-world datasets.

Abstract

Adverse weather conditions such as haze, rain, and snow often impair the quality of captured images, causing detection networks trained on normal images to generalize poorly in these scenarios. In this paper, we raise an intriguing question - if the combination of image restoration and object detection, can boost the performance of cutting-edge detectors in adverse weather conditions. To answer it, we propose an effective yet unified detection paradigm that bridges these two subtasks together via dynamic enhancement learning to discern objects in adverse weather conditions, called TogetherNet. Different from existing efforts that intuitively apply image dehazing/deraining as a pre-processing step, TogetherNet considers a multi-task joint learning problem. Following the joint learning scheme, clean features produced by the restoration network can be shared to learn better object detection in the detection network, thus helping TogetherNet enhance the detection capacity in adverse weather conditions. Besides the joint learning architecture, we design a new Dynamic Transformer Feature Enhancement module to improve the feature extraction and representation capabilities of TogetherNet. Extensive experiments on both synthetic and real-world datasets demonstrate that our TogetherNet outperforms the state-of-the-art detection approaches by a large margin both quantitatively and qualitatively. Source code is available at https://github.com/yz-wang/TogetherNet.