Saved in:
Bibliographic Details
Main Authors: Xu, Yiran, Zhong, Haoxiang, Wu, Kai, Li, Jialin, Liu, Yong, Wang, Chengjie, Xia, Shu-Tao, Liao, Hongen
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2408.16247
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914928492806144
author Xu, Yiran
Zhong, Haoxiang
Wu, Kai
Li, Jialin
Liu, Yong
Wang, Chengjie
Xia, Shu-Tao
Liao, Hongen
author_facet Xu, Yiran
Zhong, Haoxiang
Wu, Kai
Li, Jialin
Liu, Yong
Wang, Chengjie
Xia, Shu-Tao
Liao, Hongen
contents Object detectors have shown outstanding performance on various public datasets. However, annotating a new dataset for a new task is usually unavoidable in real, since 1) a single existing dataset usually does not contain all object categories needed; 2) using multiple datasets usually suffers from annotation incompletion and heterogeneous features. We propose a novel problem as "Annotation-incomplete Multi-dataset Detection", and develop an end-to-end multi-task learning architecture which can accurately detect all the object categories with multiple partially annotated datasets. Specifically, we propose an attention feature extractor which helps to mine the relations among different datasets. Besides, a knowledge amalgamation training strategy is incorporated to accommodate heterogeneous features from different sources. Extensive experiments on different object detection datasets demonstrate the effectiveness of our methods and an improvement of 2.17%, 2.10% in mAP can be achieved on COCO and VOC respectively.
format Preprint
id arxiv_https___arxiv_org_abs_2408_16247
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Anno-incomplete Multi-dataset Detection
Xu, Yiran
Zhong, Haoxiang
Wu, Kai
Li, Jialin
Liu, Yong
Wang, Chengjie
Xia, Shu-Tao
Liao, Hongen
Computer Vision and Pattern Recognition
Object detectors have shown outstanding performance on various public datasets. However, annotating a new dataset for a new task is usually unavoidable in real, since 1) a single existing dataset usually does not contain all object categories needed; 2) using multiple datasets usually suffers from annotation incompletion and heterogeneous features. We propose a novel problem as "Annotation-incomplete Multi-dataset Detection", and develop an end-to-end multi-task learning architecture which can accurately detect all the object categories with multiple partially annotated datasets. Specifically, we propose an attention feature extractor which helps to mine the relations among different datasets. Besides, a knowledge amalgamation training strategy is incorporated to accommodate heterogeneous features from different sources. Extensive experiments on different object detection datasets demonstrate the effectiveness of our methods and an improvement of 2.17%, 2.10% in mAP can be achieved on COCO and VOC respectively.
title Anno-incomplete Multi-dataset Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2408.16247