A Survey of Zero-Shot Object Detection

Zero-Shot object Detection (ZSD), one of the most challenging problems in the field of object detection, aims to accurately identify new categories that are not encountered during training. Recent advancements in deep learning and increased computational power have led to significant improvements in...

Full description

Saved in:
Bibliographic Details
Main Authors: Weipeng Cao, Xuyang Yao, Zhiwu Xu, Ye Liu, Yinghui Pan, Zhong Ming
Format: Article
Language:English
Published: Tsinghua University Press 2025-05-01
Series:Big Data Mining and Analytics
Subjects:
Online Access:https://www.sciopen.com/article/10.26599/BDMA.2024.9020098
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849304127973097472
author Weipeng Cao
Xuyang Yao
Zhiwu Xu
Ye Liu
Yinghui Pan
Zhong Ming
author_facet Weipeng Cao
Xuyang Yao
Zhiwu Xu
Ye Liu
Yinghui Pan
Zhong Ming
author_sort Weipeng Cao
collection DOAJ
description Zero-Shot object Detection (ZSD), one of the most challenging problems in the field of object detection, aims to accurately identify new categories that are not encountered during training. Recent advancements in deep learning and increased computational power have led to significant improvements in object detection systems, achieving high recognition accuracy on benchmark datasets. However, these systems remain limited in real-world applications due to the scarcity of labeled training samples, making it difficult to detect unseen classes. To address this, researchers have explored various approaches, yielding promising progress. This article provides a comprehensive review of the current state of ZSD, distinguishing four related methods—zero-shot, open-vocabulary, open-set, and open-world approaches—based on task objectives and data usage. We highlight representative methods, discuss the technical challenges within each framework, and summarize the commonly used evaluation metrics, benchmark datasets, and experimental results. Our review aims to offer readers a clear overview of the latest developments and performance trends in ZSD.
format Article
id doaj-art-6dd9dd48a638454e957955d34d2550c3
institution Kabale University
issn 2096-0654
2097-406X
language English
publishDate 2025-05-01
publisher Tsinghua University Press
record_format Article
series Big Data Mining and Analytics
spelling doaj-art-6dd9dd48a638454e957955d34d2550c32025-08-20T03:55:49ZengTsinghua University PressBig Data Mining and Analytics2096-06542097-406X2025-05-018372675010.26599/BDMA.2024.9020098A Survey of Zero-Shot Object DetectionWeipeng Cao0Xuyang Yao1Zhiwu Xu2Ye Liu3Yinghui Pan4Zhong Ming5Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen), Shenzhen 518107, China, and also with the National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, ChinaNational Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen 518060, ChinaCollege of Computer Science and Software Engineering, Shenzhen University, Shenzhen 518060, ChinaZero-Shot object Detection (ZSD), one of the most challenging problems in the field of object detection, aims to accurately identify new categories that are not encountered during training. Recent advancements in deep learning and increased computational power have led to significant improvements in object detection systems, achieving high recognition accuracy on benchmark datasets. However, these systems remain limited in real-world applications due to the scarcity of labeled training samples, making it difficult to detect unseen classes. To address this, researchers have explored various approaches, yielding promising progress. This article provides a comprehensive review of the current state of ZSD, distinguishing four related methods—zero-shot, open-vocabulary, open-set, and open-world approaches—based on task objectives and data usage. We highlight representative methods, discuss the technical challenges within each framework, and summarize the commonly used evaluation metrics, benchmark datasets, and experimental results. Our review aims to offer readers a clear overview of the latest developments and performance trends in ZSD.https://www.sciopen.com/article/10.26599/BDMA.2024.9020098zero-shot object detection (zsd)open-vocabulary object detectionopen-set object detectionopen-world object detection
spellingShingle Weipeng Cao
Xuyang Yao
Zhiwu Xu
Ye Liu
Yinghui Pan
Zhong Ming
A Survey of Zero-Shot Object Detection
Big Data Mining and Analytics
zero-shot object detection (zsd)
open-vocabulary object detection
open-set object detection
open-world object detection
title A Survey of Zero-Shot Object Detection
title_full A Survey of Zero-Shot Object Detection
title_fullStr A Survey of Zero-Shot Object Detection
title_full_unstemmed A Survey of Zero-Shot Object Detection
title_short A Survey of Zero-Shot Object Detection
title_sort survey of zero shot object detection
topic zero-shot object detection (zsd)
open-vocabulary object detection
open-set object detection
open-world object detection
url https://www.sciopen.com/article/10.26599/BDMA.2024.9020098
work_keys_str_mv AT weipengcao asurveyofzeroshotobjectdetection
AT xuyangyao asurveyofzeroshotobjectdetection
AT zhiwuxu asurveyofzeroshotobjectdetection
AT yeliu asurveyofzeroshotobjectdetection
AT yinghuipan asurveyofzeroshotobjectdetection
AT zhongming asurveyofzeroshotobjectdetection
AT weipengcao surveyofzeroshotobjectdetection
AT xuyangyao surveyofzeroshotobjectdetection
AT zhiwuxu surveyofzeroshotobjectdetection
AT yeliu surveyofzeroshotobjectdetection
AT yinghuipan surveyofzeroshotobjectdetection
AT zhongming surveyofzeroshotobjectdetection