{"id":{"repo_id":"vt","oai_identifier":"oai:vtechworks.lib.vt.edu:10919/101988"},"canonical_url":"https://search.dev.ndltd.org/etd/vt/oai:vtechworks.lib.vt.edu:10919/101988","repository":{"repo_id":"vt","name":"Virginia Tech","base_url":"https://vtechworks.lib.vt.edu/oai/request"},"display":{"title":"Addressing Occlusion in Panoptic Segmentation","abstract":"Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite the gains in performance, image understanding algorithms are still not completely robust to partial occlusion. In this work, we propose a novel object classification method based on compositional modeling and explore its effect in the context of the newly introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection pipeline in UPSNet, a Mask R-CNN based design for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. We perform extensive experiments and showcase results on the complex COCO and Cityscapes datasets. The novel classification method shows promising results for object classification on occluded instances in complex scenes.","abstract_html":"Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite the gains in performance, image understanding algorithms are still not completely robust to partial occlusion. In this work, we propose a novel object classification method based on compositional modeling and explore its effect in the context of the newly introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection pipeline in UPSNet, a Mask R-CNN based design for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. We perform extensive experiments and showcase results on the complex COCO and Cityscapes datasets. The novel classification method shows promising results for object classification on occluded instances in complex scenes.","abstract_has_math":false,"creators":["Sarkaar, Ajit Bhikamsingh"],"institution":"Virginia Tech","degree_name":null,"degree_level":"masters","degree_discipline":null,"degree_department":"Computer Engineering","school":null,"contributors":[],"advisors":[],"committee_chairs":["Abbott, A. Lynn"],"committee_members":["Huang, Bert","Jones, Creed F. III"],"year":2021,"date_issued":"2021-01-20","date_published":"2021-01-20","updated_at":"2026-07-22T22:19:54Z","subjects":["Deep learning (Machine learning)","Image Segmentation","Object Detection","Image Classification","Autonomous Systems"],"languages":[],"rights":["In Copyright"],"rights_urls":["http://rightsstatements.org/vocab/InC/1.0/"],"identifier_entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:29107"],"render_values":[{"text":"vt_gsexam:29107","href":null,"code":true}]}]},"links":{"outbound_url":"http://hdl.handle.net/10919/101988","outbound_label":"Handle","outbound_source":"dc:identifier.uri"},"metadata_groups":[{"id":"people","label":"People","entries":[{"key":"dc:contributor.committeechair","label":"Committee Chair","values":["Abbott, A. Lynn"]},{"key":"dc:contributor.committeemember","label":"Committee Member","values":["Huang, Bert","Jones, Creed F. III"]},{"key":"dc:contributor.department","label":"Department","values":["Computer Engineering"]},{"key":"dc:creator","label":"Author","values":["Sarkaar, Ajit Bhikamsingh"]}]},{"id":"academic_context","label":"Academic Context","entries":[{"key":"dc:date.accessioned","label":"Dc Date Accessioned","values":["2021-01-21T09:00:22Z"]},{"key":"dc:date.available","label":"Dc Date Available","values":["2021-01-21T09:00:22Z"]},{"key":"dc:date.issued","label":"Date","values":["2021-01-20"]},{"key":"dc:publisher","label":"Institution","values":["Virginia Tech"]},{"key":"dc:type","label":"Dc Type","values":["Thesis"]},{"key":"thesis:degree_level","label":"Degree Level","values":["masters"]},{"key":"thesis:institution_name","label":"Thesis Institution Name","values":["Virginia Polytechnic Institute and State University"]}]},{"id":"subjects_keywords","label":"Subjects and Keywords","entries":[{"key":"dc:subject","label":"Dc Subject","values":["Deep learning (Machine learning)","Image Segmentation","Object Detection","Image Classification","Autonomous Systems"]}]},{"id":"language_rights","label":"Language and Rights","entries":[{"key":"dc:rights","label":"Dc Rights","values":["In Copyright"]},{"key":"dc:rights.uri","label":"Rights URI","values":["http://rightsstatements.org/vocab/InC/1.0/"]}]},{"id":"identifiers","label":"Identifiers","entries":[{"key":"dc:identifier.other","label":"Dc Identifier Other","values":["vt_gsexam:29107"]},{"key":"dc:identifier.uri","label":"Identifier URI","values":["http://hdl.handle.net/10919/101988"]}]},{"id":"additional","label":"Additional Metadata","entries":[{"key":"dc:description.abstract","label":"Abstract","values":["Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite the gains in performance, image understanding algorithms are still not completely robust to partial occlusion. In this work, we propose a novel object classification method based on compositional modeling and explore its effect in the context of the newly introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection pipeline in UPSNet, a Mask R-CNN based design for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. We perform extensive experiments and showcase results on the complex COCO and Cityscapes datasets. The novel classification method shows promising results for object classification on occluded instances in complex scenes."]},{"key":"dc:description.abstractgeneral","label":"General Abstract","values":["Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite making significant improvements, algorithms for these tasks still do not perform well at recognizing partially visible objects in the scene. In this work, we propose a novel object classification method that uses compositional models to perform part based detection. The method first looks at individual parts of an object in the scene and then makes a decision about its identity. We test the proposed method in the context of the recently introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection module in UPSNet, a Mask R-CNN based algorithm for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. After performing extensive experiments and evaluation, it can be seen that the novel classification method shows promising results for object classification on occluded instances in complex scenes."]},{"key":"dc:description.degree","label":"Dc Description Degree","values":["Master of Science"]},{"key":"dc:format.medium","label":"Dc Format Medium","values":["ETD"]},{"key":"dc:title","label":"Title","values":["Addressing Occlusion in Panoptic Segmentation"]}]}],"canonical_facts":{"dc:contributor.committeechair":["Abbott, A. Lynn"],"dc:contributor.committeemember":["Huang, Bert","Jones, Creed F. III"],"dc:contributor.department":["Computer Engineering"],"dc:creator":["Sarkaar, Ajit Bhikamsingh"],"dc:date.accessioned":["2021-01-21T09:00:22Z"],"dc:date.available":["2021-01-21T09:00:22Z"],"dc:date.issued":["2021-01-20"],"dc:description.abstract":["Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite the gains in performance, image understanding algorithms are still not completely robust to partial occlusion. In this work, we propose a novel object classification method based on compositional modeling and explore its effect in the context of the newly introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection pipeline in UPSNet, a Mask R-CNN based design for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. We perform extensive experiments and showcase results on the complex COCO and Cityscapes datasets. The novel classification method shows promising results for object classification on occluded instances in complex scenes."],"dc:description.abstractgeneral":["Visual recognition tasks have witnessed vast improvements in performance since the advent of deep learning. Despite making significant improvements, algorithms for these tasks still do not perform well at recognizing partially visible objects in the scene. In this work, we propose a novel object classification method that uses compositional models to perform part based detection. The method first looks at individual parts of an object in the scene and then makes a decision about its identity. We test the proposed method in the context of the recently introduced panoptic segmentation task. The panoptic segmentation task combines both semantic and instance segmentation to perform labelling of the entire image. The novel classification method replaces the object detection module in UPSNet, a Mask R-CNN based algorithm for panoptic segmentation. We also discuss an issue with the segmentation mask prediction of Mask R-CNN that affects overlapping instances. After performing extensive experiments and evaluation, it can be seen that the novel classification method shows promising results for object classification on occluded instances in complex scenes."],"dc:description.degree":["Master of Science"],"dc:format.medium":["ETD"],"dc:identifier.other":["vt_gsexam:29107"],"dc:identifier.uri":["http://hdl.handle.net/10919/101988"],"dc:publisher":["Virginia Tech"],"dc:rights":["In Copyright"],"dc:rights.uri":["http://rightsstatements.org/vocab/InC/1.0/"],"dc:subject":["Deep learning (Machine learning)","Image Segmentation","Object Detection","Image Classification","Autonomous Systems"],"dc:title":["Addressing Occlusion in Panoptic Segmentation"],"dc:type":["Thesis"],"thesis:degree_level":["masters"],"thesis:institution_name":["Virginia Polytechnic Institute and State University"]},"updated_at":"2026-07-22T22:19:54Z"}