2026-09-20T16:46:19Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/116182 2023-07-11 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Schwing, Alexander Schwing, Alexander Shi, Humphrey Hasegawa-Johnson, Mark Darrell, Trevor Liang, Zhi-Pei 2022-08 application/pdf en text Submission original under an indefinite embargo labeled 'Open Access'. The submission was exported from vireo on 2022-11-15 without embargo terms The student, Bowen Cheng, accepted the attached license on 2022-07-05 at 10:22. The student, Bowen Cheng, submitted this Dissertation for approval on 2022-07-05 at 10:28. This Dissertation was approved for publication on 2022-07-06 at 16:20. DSpace SAF Submission Ingestion Package generated from Vireo submission #18142 on 2022-11-15 at 17:38:09 From pixels to regions: Toward universal image segmentation Cheng, Bowen 2022-07-06 computer vision image segmentation semantic segmentation instance segmentation panoptic segmentation Image segmentation is about grouping pixels with different semantics, e.g., category or instance membership, where each choice of semantics defines a task. While only the semantics of each task differ, current research focuses on designing specialized architectures for each task: semantic segmentation is usually formulated as per-pixel classification and mask classification dominates instance-level segmentation tasks. In this dissertation, we demonstrate how to build a single unified architecture that can address any image segmentation task. We first introduce an effort in unifying image segmentation with either per-pixel classification (Panoptic-DeepLab) or mask classification (MaskFormer). We observe mask classification is sufficiently general to solve both semantic- and instance-level segmentation tasks. Based on this observation we propose Mask2Former, which outperforms even the best specialized architectures by a significant margin on four popular datasets for three image segmentation tasks (panoptic, instance and semantic). Then we discuss how to evaluate image segmentation models with a new Boundary IoU metric. Finally, we conclude this dissertation with promising future directions to explore. Thesis eng https://hdl.handle.net/2142/116182 Copyright 2022 Bowen Cheng Ph.D. Dissertation Electrical & Computer Engr University of Illinois at Urbana-Champaign Electrical & Computer Eng