{"id":{"repo_id":"uiuc","oai_identifier":"oai:www.ideals.illinois.edu:2142/108236"},"canonical_url":"https://search.dev.ndltd.org/etd/uiuc/oai:www.ideals.illinois.edu:2142/108236","repository":{"repo_id":"uiuc","name":"University of Illinois - Urbana-Champaign","base_url":"https://www.ideals.illinois.edu/oai-pmh"},"display":{"title":"Semi-supervised universal yolov3-spp with GIoU loss for autonomous driving object detection under sunny and foggy weather","abstract":"Object detection for autonomous driving has made a huge progress in recent years. However, detecting objects in foggy weather is still a challenging problem. In this thesis, we first propose a two-stage pipeline for foggy weather object detection. The two-stage pipeline removes fog from images using a Generative Adversarial Network (GAN) based model called DehazeGAN. Then, an object detection step using GIoU YOLOv3-SPP is performed on the defogged images. Following the two-stage method, we introduce a supervised universal model that deals with object detection in both sunny and foggy weather. The supervised universal model is built with a universal adapter that consists a “feature map”-based attention module and a weather-based attention module. The “feature map”-based attention module has a parallel of Squeeze-and-Excitation (SE) adapters, where each SE adapter extracts different features from each channel. The weather-based attention module looks at the input image and assigns weights to each SE adapter so that the universal adapter can describe the weather of the input image. To evaluate the performance of the supervised universal model, we established a new benchmark called CPR-A containing the following datasets: COCO, Pascal VOC, and annotated RESIDE-β. RESIDE-β only contains foggy images captured from the real world while COCO ad Pascal VOC are general object detection datasets that contain mostly clear images. We then take advantage of unannotated images in our dataset by proposing a semi-supervised universal object detection pipeline. The performance of this semi-supervised universal model is tested on CPR-U which is constructed by CPR-A and unannotated RESIDE-β. Experimentally, the trained two-stage pipeline outperforms GIoU YOLOv3-SPP by 0.17 mAP. The supervised universal model trained on CPR-A outperforms single weather/domain models (GIoU YOLOv3-SPP and the proposed two-stage model). Semi-supervised universal model further improves mAP accuracy from 0.633 to 0.654.","abstract_html":"Object detection for autonomous driving has made a huge progress in recent years. However, detecting objects in foggy weather is still a challenging problem. In this thesis, we first propose a two-stage pipeline for foggy weather object detection. The two-stage pipeline removes fog from images using a Generative Adversarial Network (GAN) based model called DehazeGAN. Then, an object detection step using GIoU YOLOv3-SPP is performed on the defogged images. Following the two-stage method, we introduce a supervised universal model that deals with object detection in both sunny and foggy weather. The supervised universal model is built with a universal adapter that consists a “feature map”-based attention module and a weather-based attention module. The “feature map”-based attention module has a parallel of Squeeze-and-Excitation (SE) adapters, where each SE adapter extracts different features from each channel. The weather-based attention module looks at the input image and assigns weights to each SE adapter so that the universal adapter can describe the weather of the input image. To evaluate the performance of the supervised universal model, we established a new benchmark called CPR-A containing the following datasets: COCO, Pascal VOC, and annotated RESIDE-β. RESIDE-β only contains foggy images captured from the real world while COCO ad Pascal VOC are general object detection datasets that contain mostly clear images. We then take advantage of unannotated images in our dataset by proposing a semi-supervised universal object detection pipeline. The performance of this semi-supervised universal model is tested on CPR-U which is constructed by CPR-A and unannotated RESIDE-β. Experimentally, the trained two-stage pipeline outperforms GIoU YOLOv3-SPP by 0.17 mAP. The supervised universal model trained on CPR-A outperforms single weather/domain models (GIoU YOLOv3-SPP and the proposed two-stage model). Semi-supervised universal model further improves mAP accuracy from 0.633 to 0.654.","abstract_has_math":false,"creators":["Jin, Zhijie"],"institution":"University of Illinois at Urbana-Champaign","degree_name":"M.S.","degree_level":"Thesis","degree_discipline":"Electrical & Computer Engr","degree_department":null,"school":null,"contributors":["Chen, Deming"],"advisors":[],"committee_chairs":[],"committee_members":[],"year":2020,"date_issued":"2020-08-27T00:46:53Z","date_published":"2020-08-27T00:46:53Z","updated_at":"2026-07-22T22:24:48Z","subjects":["Object detection","Universal Model","Autonomous driving","Semi-supervised model"],"languages":["en"],"rights":["Copyright 2020 Zhijie Jin"],"rights_urls":[],"identifier_entries":[]},"links":{"outbound_url":"http://hdl.handle.net/2142/108236","outbound_label":"Handle","outbound_source":"dc:identifier"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor","label":"Contributor","values":["Chen, Deming"]},{"key":"dc:creator","label":"Author","values":["Jin, Zhijie"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date","label":"Dc Date","values":["2020-08-27T00:46:53Z","2022-08-27T00:51:40Z","2020-05-14","2020-05"]},{"key":"dc:type","label":"Dc Type","values":["text","Thesis"]},{"key":"thesis:degree_discipline","label":"Discipline","values":["Electrical & Computer Engr"]},{"key":"thesis:degree_level","label":"Degree Level","values":["Thesis"]},{"key":"thesis:degree_name","label":"Degree Name","values":["M.S."]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["University of Illinois at Urbana-Champaign"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Object detection","Universal Model","Autonomous driving","Semi-supervised model"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:language","label":"Dc Language","values":["en"]},{"key":"dc:rights","label":"Dc Rights","values":["Copyright 2020 Zhijie Jin"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier","label":"Identifier","values":["http://hdl.handle.net/2142/108236"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description","label":"Description","values":["Object detection for autonomous driving has made a huge progress in recent years. However, detecting objects in foggy weather is still a challenging problem. In this thesis, we first propose a two-stage pipeline for foggy weather object detection. The two-stage pipeline removes fog from images using a Generative Adversarial Network (GAN) based model called DehazeGAN. Then, an object detection step using GIoU YOLOv3-SPP is performed on the defogged images. Following the two-stage method, we introduce a supervised universal model that deals with object detection in both sunny and foggy weather. The supervised universal model is built with a universal adapter that consists a “feature map”-based attention module and a weather-based attention module. The “feature map”-based attention module has a parallel of Squeeze-and-Excitation (SE) adapters, where each SE adapter extracts different features from each channel. The weather-based attention module looks at the input image and assigns weights to each SE adapter so that the universal adapter can describe the weather of the input image. To evaluate the performance of the supervised universal model, we established a new benchmark called CPR-A containing the following datasets: COCO, Pascal VOC, and annotated RESIDE-β. RESIDE-β only contains foggy images captured from the real world while COCO ad Pascal VOC are general object detection datasets that contain mostly clear images. We then take advantage of unannotated images in our dataset by proposing a semi-supervised universal object detection pipeline. The performance of this semi-supervised universal model is tested on CPR-U which is constructed by CPR-A and unannotated RESIDE-β. Experimentally, the trained two-stage pipeline outperforms GIoU YOLOv3-SPP by 0.17 mAP. The supervised universal model trained on CPR-A outperforms single weather/domain models (GIoU YOLOv3-SPP and the proposed two-stage model). Semi-supervised universal model further improves mAP accuracy from 0.633 to 0.654.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-05-01","The student, Zhijie Jin, accepted the attached license on 2020-05-14 at 10:46.","The student, Zhijie Jin, submitted this Thesis for approval on 2020-05-14 at 10:53.","This Thesis was approved for publication on 2020-05-14 at 11:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14916 on 2020-08-25 at 17:39:13","Made available in DSpace on 2020-08-27T00:46:53Z (GMT). No. of bitstreams: 2 JIN-THESIS-2020.pdf: 857579 bytes, checksum: aa837eca0862bb41724872719a89d1d3 (MD5) LICENSE.txt: 4207 bytes, checksum: 2414dc2b68872cf0d6c73ad2de8e390d (MD5) Previous issue date: 2020-05-14","Embargo set by: Seth Robbins for item 115849 Lift date: 2022-08-27T00:46:59Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 115849 Lift date: 2022-08-27T00:50:22Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 115849 Lift date: 2022-08-27T00:51:40Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"]},{"key":"dc:format","label":"Dc Format","values":["application/pdf"]},{"key":"dc:title","label":"Title","values":["Semi-supervised universal yolov3-spp with GIoU loss for autonomous driving object detection under sunny and foggy weather"]}]}],"canonical_facts":{"dc:contributor":["Chen, Deming"],"dc:creator":["Jin, Zhijie"],"dc:date":["2020-08-27T00:46:53Z","2022-08-27T00:51:40Z","2020-05-14","2020-05"],"dc:description":["Object detection for autonomous driving has made a huge progress in recent years. However, detecting objects in foggy weather is still a challenging problem. In this thesis, we first propose a two-stage pipeline for foggy weather object detection. The two-stage pipeline removes fog from images using a Generative Adversarial Network (GAN) based model called DehazeGAN. Then, an object detection step using GIoU YOLOv3-SPP is performed on the defogged images. Following the two-stage method, we introduce a supervised universal model that deals with object detection in both sunny and foggy weather. The supervised universal model is built with a universal adapter that consists a “feature map”-based attention module and a weather-based attention module. The “feature map”-based attention module has a parallel of Squeeze-and-Excitation (SE) adapters, where each SE adapter extracts different features from each channel. The weather-based attention module looks at the input image and assigns weights to each SE adapter so that the universal adapter can describe the weather of the input image. To evaluate the performance of the supervised universal model, we established a new benchmark called CPR-A containing the following datasets: COCO, Pascal VOC, and annotated RESIDE-β. RESIDE-β only contains foggy images captured from the real world while COCO ad Pascal VOC are general object detection datasets that contain mostly clear images. We then take advantage of unannotated images in our dataset by proposing a semi-supervised universal object detection pipeline. The performance of this semi-supervised universal model is tested on CPR-U which is constructed by CPR-A and unannotated RESIDE-β. Experimentally, the trained two-stage pipeline outperforms GIoU YOLOv3-SPP by 0.17 mAP. The supervised universal model trained on CPR-A outperforms single weather/domain models (GIoU YOLOv3-SPP and the proposed two-stage model). Semi-supervised universal model further improves mAP accuracy from 0.633 to 0.654.","Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2022-05-01","The student, Zhijie Jin, accepted the attached license on 2020-05-14 at 10:46.","The student, Zhijie Jin, submitted this Thesis for approval on 2020-05-14 at 10:53.","This Thesis was approved for publication on 2020-05-14 at 11:53.","DSpace SAF Submission Ingestion Package generated from Vireo submission #14916 on 2020-08-25 at 17:39:13","Made available in DSpace on 2020-08-27T00:46:53Z (GMT). No. of bitstreams: 2 JIN-THESIS-2020.pdf: 857579 bytes, checksum: aa837eca0862bb41724872719a89d1d3 (MD5) LICENSE.txt: 4207 bytes, checksum: 2414dc2b68872cf0d6c73ad2de8e390d (MD5) Previous issue date: 2020-05-14","Embargo set by: Seth Robbins for item 115849 Lift date: 2022-08-27T00:46:59Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 115849 Lift date: 2022-08-27T00:50:22Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Embargo set by: Seth Robbins for item 115849 Lift date: 2022-08-27T00:51:40Z Reason: Author requested closed access (OA after 2yrs) in Vireo ETD system","Author requested closed access (OA after 2yrs) in Vireo ETD system","Limited"],"dc:format":["application/pdf"],"dc:identifier":["http://hdl.handle.net/2142/108236"],"dc:language":["en"],"dc:rights":["Copyright 2020 Zhijie Jin"],"dc:subject":["Object detection","Universal Model","Autonomous driving","Semi-supervised model"],"dc:title":["Semi-supervised universal yolov3-spp with GIoU loss for autonomous driving object detection under sunny and foggy weather"],"dc:type":["text","Thesis"],"thesis:degree_discipline":["Electrical & Computer Engr"],"thesis:degree_level":["Thesis"],"thesis:degree_name":["M.S."],"thesis:institution_name":["University of Illinois at Urbana-Champaign"]},"updated_at":"2026-07-22T22:24:48Z"}