Improving Object Detection Quality by Incorporating Global Contexts via Self-Attention
Fully convolutional structures provide feature maps acquiring local contexts of an image by only stacking numerous convolutional layers. These structures are known to be effective in modern state-of-the-art object detectors such as Faster R-CNN and SSD to find objects from local contexts. However, t...
Main Authors: | Donghyeon Lee, Joonyoung Kim, Kyomin Jung |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-01-01
|
Series: | Electronics |
Subjects: | |
Online Access: | https://www.mdpi.com/2079-9292/10/1/90 |
Similar Items
-
Object Detection Algorithm Based on Context Information and Self-Attention Mechanism
by: Hong Liang, et al.
Published: (2022-04-01) -
Spectral and Spatial Global Context Attention for Hyperspectral Image Classification
by: Zhongwei Li, et al.
Published: (2021-02-01) -
Fusing Context Features and Spatial Attention to Improve Object Detection
by: Tianjia Liu, et al.
Published: (2023-03-01) -
ACSiamRPN: Adaptive Context Sampling for Visual Object Tracking
by: Xiaofei Qin, et al.
Published: (2020-09-01) -
Few-Shot Object Detection in Remote Sensing Imagery via Fuse Context Dependencies and Global Features
by: Bin Wang, et al.
Published: (2023-07-01)