SIGVIS/GRAPHICS SEMINAR - Rohit Venkata Sai Dulam (VIMS Lab)
Auto-DeepLab: Hierarchical Neural Architecture Search for Semantic Image Segmentation
Abstract: Recently, Neural Architecture Search (NAS) has successfully identified neural network architectures that exceed human-designed ones on large-scale image classification. In this paper, we study NAS for semantic image segmentation. Existing works often focus on searching the repeatable cell structure, while hand-designing the outer network structure that controls the spatial resolution changes. This choice simplifies the search space but becomes increasingly problematic for dense image prediction which exhibits a lot more network-level architectural variations. Therefore, we propose to search the network level structure in addition to the cell level structure, which forms a hierarchical architecture search space. We present a network-level search space that includes many popular designs and develops a formulation that allows efficient gradient-based architecture search (3 P100 GPU days on Cityscapes images). We demonstrate the effectiveness of the proposed method on the challenging Cityscapes, PASCAL VOC 2012, and ADE20K datasets. Auto-DeepLab, our architecture searched specifically for semantic image segmentation, attains state-of-the-art performance without any ImageNet pretraining.
Dial-In Information
https://udel.zoom.us/j/95713763857
Wednesday, November 11, 2020 at 1:25pm to 2:40pm
Virtual Event- Event Type
- Calendar
- Departments
- Website
- Group
- ENGR - Computer & Information Sciences
- Contact Email
- Contact Name
-
Kristin Halberg
- Contact Phone
-
302-831-2711
- Subscribe
Recent Activity
No recent activity