CrossDet++: Growing Crossline Representation for Object Detection

In object detection, precise object representation is a key factor to successfully classify and locate objects of an image. Existing methods usually use rectangular anchor boxes or a set of points to represent objects. However, these methods either introduce background noise or miss the continuous a...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on circuits and systems for video technology 2023-03, Vol.33 (3), p.1093-1108
Main Authors: Qiu, Heqian, Li, Hongliang, Wu, Qingbo, Cui, Jianhua, Song, Zichen, Wang, Lanxiao, Zhang, Minjian
Format: Article
Language:English
Subjects:
axis-query crossline growing
Background noise
crossline representation
decoupled regression
Detectors
Feature extraction
Image classification
Object detection
Object recognition
Optimization
Proposals
Representations
semantic richness
Semantics
Training
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In object detection, precise object representation is a key factor to successfully classify and locate objects of an image. Existing methods usually use rectangular anchor boxes or a set of points to represent objects. However, these methods either introduce background noise or miss the continuous appearance information inside the object, and thus cause incorrect detection results. In this paper, we propose a novel anchor-free object detection network, called CrossDet++, which uses a set of growing crosslines along horizontal and vertical axes as object representations. An object can be flexibly represented as crosslines in different combinations, which inspires us to select the expressive crossline to effectively reduce the interference of noise. Meanwhile, the crossline representation takes into account the continuous adjacent object information, which is useful to enhance the discriminability of object features and find the object boundaries. Based on the learned crosslines, we propose an axis-query crossline growing module to adaptively capture features of crosslines and query surrounding pixels related to the line features for subsequent growing of crosslines. Their growing offsets and scales can be supervised by a decoupled regression mechanism, which limits the regression target to a specific direction for decreasing the optimization difficulty. During the training, we design a semantic-guided label assignment to emphasize the importance of crossline targets with higher semantic richness, further improving the detection performance. The experiment results demonstrate the effectiveness of our proposed method. Code can be available at: https://github.com/QiuHeqian/CrossDet .
ISSN:1051-8215
1558-2205
DOI:10.1109/TCSVT.2022.3211734