Single Stage Class Agnostic Common Object Detection: A Simple Baseline

Chuong Nguyen, Thuy Nguyen, Anh Vo, Yamazaki Masayuki

Abstract

This paper addresses the problem of common object detection, which aims to detect objects of similar categories from a set of images. Although it shares some similarities with the standard object detection and co-segmentation, common object detection, recently promoted by (Jiang et al., 2019), has some unique advantages and challenges. First, it is designed to work on both closed-set and open-set conditions, a.k.a. known and unknown objects. Second, it must be able to match objects of the same category but not restricted to the same instance, texture, or posture. Third, it can distinguish multiple objects. In this work, we introduce the Single Stage Common Object Detection (SSCOD) to detect class-agnostic common objects from an image set. The proposed method is built upon the standard single-stage object detector. Furthermore, an embedded branch is introduced to generate the object’s representation feature, and their similarity is measured by cosine distance. Experiments are conducted on PASCAL VOC 2007 and COCO 2014 datasets. While being simple and flexible, our proposed SSCOD built upon ATSSNet performs significantly better than the baseline of the standard object detection, while still be able to match objects of unknown categories. Our source code can be found at (URL).

Download


Paper Citation


in Harvard Style

Nguyen C., Nguyen T., Vo A. and Masayuki Y. (2021). Single Stage Class Agnostic Common Object Detection: A Simple Baseline.In Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-758-486-2, pages 396-407. DOI: 10.5220/0010242303960407


in Bibtex Style

@conference{icpram21,
author={Chuong Nguyen and Thuy Nguyen and Anh Vo and Yamazaki Masayuki},
title={Single Stage Class Agnostic Common Object Detection: A Simple Baseline},
booktitle={Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2021},
pages={396-407},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010242303960407},
isbn={978-989-758-486-2},
}


in EndNote Style

TY - CONF

JO - Proceedings of the 10th International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Single Stage Class Agnostic Common Object Detection: A Simple Baseline
SN - 978-989-758-486-2
AU - Nguyen C.
AU - Nguyen T.
AU - Vo A.
AU - Masayuki Y.
PY - 2021
SP - 396
EP - 407
DO - 10.5220/0010242303960407