Abstract
Semantic segmentation is a challenging task that needs to handle large scale variations, deformations, and different viewpoints. In this paper, we develop a novel network named Gated Path Selection Network (GPSNet), which aims to adaptively select receptive fields while maintaining the dense sampling capability. In GPSNet, we first design a two-dimensional SuperNet, which densely incorporates features from growing receptive fields. And then, a Comparative Feature Aggregation (CFA) module is introduced to dynamically aggregate discriminative semantic context. In contrast to previous works that focus on optimizing sparse sampling locations on regular grids, GPSNet can adaptively harvest free form dense semantic context information. The derived adaptive receptive fields and dense sampling locations are data-dependent and flexible which can model various contexts of objects. On two representative semantic segmentation datasets, i.e., Cityscapes and ADE20K, we show that the proposed approach consistently outperforms previous methods without bells and whistles.
Original language | English |
---|---|
Article number | 9318517 |
Pages (from-to) | 2436-2449 |
Number of pages | 14 |
Journal | IEEE Transactions on Image Processing |
Volume | 30 |
DOIs | |
State | Published - 2021 |
Bibliographical note
Publisher Copyright:© 2021 IEEE.
Keywords
- Semantic segmentation
- adaptive context aggregation
- adaptive receptive fields and sampling locations
- local discriminative feature
ASJC Scopus subject areas
- Software
- Computer Graphics and Computer-Aided Design