2 options
Learning image segmentation with relation-centric loss and representation / Jyh-Jing Hwang.
- Format:
- Book
- Thesis/Dissertation
- Author/Creator:
- Hwang, Jyh-Jing, author.
- Language:
- English
- Subjects (All):
- Computer science.
- Artificial intelligence.
- Computer and Information Science--Penn dissertations.
- Penn dissertations--Computer and Information Science.
- Local Subjects:
- Computer science.
- Artificial intelligence.
- Computer and Information Science--Penn dissertations.
- Penn dissertations--Computer and Information Science.
- Genre:
- Academic theses.
- Physical Description:
- 1 online resource (155 pages)
- Contained In:
- Dissertations Abstracts International 81-12B.
- Place of Publication:
- [Philadelphia, Pennsylvania] : University of Pennsylvania ; Ann Arbor : ProQuest Dissertations & Theses, 2020.
- Language Note:
- English
- System Details:
- Mode of access: World Wide Web.
- text file
- Summary:
- How to equip machines with the ability to understand an image and explain everything in it has a long history in computer vision, motivating tasks from image recognition, detection, and segmentation towards holistic scene understanding. Researchers have been tackling an array of related structured prediction tasks to approach this problem: low-level and high-level image segmentation, monocular image depth estimation, surface normal prediction, etc. These tasks focus on different aspects of holistic image understanding yet intertwine with one another to unveil underlying image structures. This dissertation presents our efforts in this direction, with an emphasis on learning to model pixel relationships.We identify three major problems in image understanding and segmentation: (1) The pixel-wise classification based approaches fundamentally lack the sense of object structures and spatial layouts. (2) The lack of explainability prevents us from understanding the mistakes and from proposing remedies accordingly. (3) The definition of image segmentation is ambiguous and changing over time. These constant arguments reveal the complexity of holistic image understanding and motivate us to propose unsupervised feature learning for image segmentation.To tackle these problems one by one, we first propose Adaptive Affinity Fields (AAF) for semantic segmentation, which capture and match the semantic relations between neighboring pixels in the label space. Furthermore, we generalize the affinity fields in AAF as another neural network and propose Adversarial Structure Matching (ASM) for structured prediction tasks. ASM extends the structure learning concept from segmentation to monocular depth estimation and surface normal prediction. To tackle the second and third problems, we turn attention to metric learning and propose Segment Sorting (SegSort) for semantic segmentation. Most excitingly, SegSort is the first attempt using deep learning for unsupervised semantic segmentation with interpretable results. Last but not least, we extend our proposed SegSort to image parsing as a first attempt to unify semantic and instance segmentation.
- Notes:
- Source: Dissertations Abstracts International, Volume: 81-12, Section: B.
- Advisors: Shi, Jianbo; Yu, Stella X.; Committee members: Konstantinos Daniilidis; Camillo Taylor; Dinesh Jayaraman; Alexei Efros.
- Department: Computer and Information Science.
- Ph.D. University of Pennsylvania 2020.
- Local Notes:
- School code: 0175
- ISBN:
- 9798617032163
- Access Restriction:
- Restricted for use by site license.
- This item is not available from ProQuest Dissertations & Theses.
- This item must not be sold to any third party vendors.
The Penn Libraries is committed to describing library materials using current, accurate, and responsible language. If you discover outdated or inaccurate language, please fill out this feedback form to report it and suggest alternative language.