Publication Type
Conference Proceeding Article
Version
acceptedVersion
Publication Date
8-2020
Abstract
Feature interactions across space and scales underpin modern visual recognition systems because they introduce beneficial visual contexts. Conventionally, spatial contexts are passively hidden in the CNN’s increasing receptive fields or actively encoded by non-local convolution. Yet, the non-local spatial interactions are not across scales, and thus they fail to capture the non-local contexts of objects (or parts) residing in different scales. To this end, we propose a fully active feature interaction across both space and scales, called Feature Pyramid Transformer (FPT). It transforms any feature pyramid into another feature pyramid of the same size but with richer contexts, by using three specially designed transformers in self-level, top-down, and bottom-up interaction fashion. FPT serves as a generic visual backbone with fair computational overhead. We conduct extensive experiments in both instance-level ( i . e., object detection and instance segmentation) and pixel-level segmentation tasks, using various backbones and head networks, and observe consistent improvement over all the baselines and the state-of-the-art methods
Keywords
Feature pyramid, Visual context, Transformer, Object detection, Instance segmentation, Semantic segmentation
Discipline
Artificial Intelligence and Robotics | Databases and Information Systems
Research Areas
Data Science and Engineering
Publication
Computer vision: ECCV 2020, 16th European Conference, Glasgow, Virtual, August 23-28, Proceedings
Volume
12373
First Page
323
Last Page
339
ISBN
9783030586034
Identifier
10.1007/978-3-030-58604-1_20
Publisher
Springer
City or Country
Cham
Citation
ZHANG, Dong; ZHANG, Hanwang; TANG, Jinhui; WANG, Meng; HUA, Xian-Sheng; and SUN, Qianru.
Feature pyramid transformer. (2020). Computer vision: ECCV 2020, 16th European Conference, Glasgow, Virtual, August 23-28, Proceedings. 12373, 323-339.
Available at: https://ink.library.smu.edu.sg/sis_research/5595
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1007/978-3-030-58604-1_20
