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

Simple item page
dc.contributor.authorWang, Yongzhenen_US
dc.contributor.authorYan, Xuefengen_US
dc.contributor.authorZhang, Kaiwenen_US
dc.contributor.authorGong, Linaen_US
dc.contributor.authorXie, Haoranen_US
dc.contributor.authorWang, Fu Leeen_US
dc.contributor.authorWei, Mingqiangen_US
dc.contributor.editorUmetani, Nobuyukien_US
dc.contributor.editorWojtan, Chrisen_US
dc.contributor.editorVouga, Etienneen_US
dc.date.accessioned2022-10-04T06:41:31Z
dc.date.available2022-10-04T06:41:31Z
dc.date.issued2022
dc.description.abstractAdverse 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.en_US
dc.description.number7
dc.description.sectionheadersImage Restoration
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume41
dc.identifier.doi10.1111/cgf.14692
dc.identifier.issn1467-8659
dc.identifier.pages465-476
dc.identifier.pages12 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.14692
dc.identifier.urihttps://diglib.eg.org:443/handle/10.1111/cgf14692
dc.publisherThe Eurographics Association and John Wiley & Sons Ltd.en_US
dc.subjectKeywords: TogetherNet, Object detection, Image restoration, Adverse weather, Joint learning, Dynamic transformer feature enhancement CCS Concepts: Computing methodologies → Object detection
dc.subjectTogetherNet
dc.subjectObject detection
dc.subjectImage restoration
dc.subjectAdverse weather
dc.subjectJoint learning
dc.subjectDynamic transformer feature enhancement CCS Concepts
dc.subjectComputing methodologies → Object detection
dc.titleTogetherNet: Bridging Image Restoration and Object Detection Together via Dynamic Enhancement Learningen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
v41i7pp465-476.pdf
Size:
6.06 MB
Format:
Adobe Portable Document Format
Download
Collections
41-Issue 7