Analysis of Visual Reasoning on One-Stage Object Detection

Current state-of-the-art one-stage object detectors are limited by treating each image region separately without considering possible relations of the objects. This causes dependency solely on high-quality convolutional feature representations for detecting objects successfully. However, this may no...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Aksoy, Tolga, Halici, Ugur
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 26.02.2022
Subjects
Object recognition
Reasoning
Online AccessGet full text

Cover

More Information
Summary:Current state-of-the-art one-stage object detectors are limited by treating each image region separately without considering possible relations of the objects. This causes dependency solely on high-quality convolutional feature representations for detecting objects successfully. However, this may not be possible sometimes due to some challenging conditions. In this paper, the usage of reasoning features on one-stage object detection is analyzed. We attempted different architectures that reason the relations of the image regions by using self-attention. YOLOv3-Reasoner2 model spatially and semantically enhances features in the reasoning layer and fuses them with the original convolutional features to improve performance. The YOLOv3-Reasoner2 model achieves around 2.5% absolute improvement with respect to baseline YOLOv3 on COCO in terms of mAP while still running in real-time.
ISSN:2331-8422