FoveaBox: Beyound Anchor-Based Object Detection

We present FoveaBox, an accurate, flexible, and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generali...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on image processing Vol. 29; pp. 7389 - 7398
Main Authors: Kong, Tao, Sun, Fuchun, Liu, Huaping, Jiang, Yuning, Li, Lei, Shi, Jianbo
Format: Journal Article
Language:English
Published: New York IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
anchor free
Anchors
Aspect ratio
Bells
Benchmarks
Boxes
Detectors
Feature extraction
foveabox
Object detection
Object recognition
Parameter sensitivity
Proposals
Sun
Training
Visualization
ISSN:1057-7149, 1941-0042
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:We present FoveaBox, an accurate, flexible, and completely anchor-free framework for object detection. While almost all state-of-the-art object detectors utilize predefined anchors to enumerate possible locations, scales and aspect ratios for the search of the objects, their performance and generalization ability are also limited to the design of anchors. Instead, FoveaBox directly learns the object existing possibility and the bounding box coordinates without anchor reference. This is achieved by: (a) predicting category-sensitive semantic maps for the object existing possibility, and (b) producing category-agnostic bounding box for each position that potentially contains an object. The scales of target boxes are naturally associated with feature pyramid representations. In FoveaBox, an instance is assigned to adjacent feature levels to make the model more accurate.We demonstrate its effectiveness on standard benchmarks and report extensive experimental analysis. Without bells and whistles, FoveaBox achieves state-of-the-art single model performance on the standard COCO and Pascal VOC object detection benchmark. More importantly, FoveaBox avoids all computation and hyper-parameters related to anchor boxes, which are often sensitive to the final detection performance. We believe the simple and effective approach will serve as a solid baseline and help ease future research for object detection. The code has been made publicly available at https://github.com/taokong/FoveaBox.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1057-7149
1941-0042
DOI:10.1109/TIP.2020.3002345