Home Research Papers Datasets State of the Art Pricing

Discover, visualize, and connect AI research papers. Explore the latest trends and insights in artificial intelligence research.

Product

Home
Research Papers
About

Support

Contact
Terms of Service
Privacy Policy

© 2026 Papersgraph. All rights reserved.

computer-vision

Open World Object Detection

3260 papers • 126 benchmarks • 313 datasets

Open World Object Detection is a computer vision problem where a model is tasked to: 1) identify objects that have not been introduced to it as `unknown', without explicit supervision to do so, and 2) incrementally learn these identified unknown categories without forgetting previously learned classes, when the corresponding labels are progressively received.

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in open-world-object-detection

Trend

Dataset

Best Model

Actions

PASCAL VOC 2007

PASCAL VOC 2007

COCO 2017 (Outdoor, Accessories, Appliance, Truck)

COCO 2017 (Outdoor, Accessories, Appliance, Truck)

Libraries

i

Use these libraries to find open-world-object-detection models and implementations

ArminLee/OWOD_Review

4 papers 17

Datasets

PASCAL VOC 2007

PASCAL VOC 2007

UVO

COCO-OOD

COCO-Mix

SFCHD

Subtasks

No subtasks available.

Most implemented papers

Learning Open-World Object Proposals without Learning to Classify

Tsung-Yi Lin, In-So Kweon, Weicheng Kuo, A. Angelova, Dahun Kim•Sat Aug 14 2021

A classification-free Object Localization Network (OLN) is proposed which estimates the objectness of each region purely by how well the location and shape of a region overlap with any ground-truth object.

155

Content

Introduction Benchmarks Datasets Subtasks Libraries Papers

COCO 2017 (Sports, Food)

COCO 2017 (Sports, Food)

COCO 2017 (Electronic, Indoor, Kitchen, Furniture)

COCO 2017 (Electronic, Indoor, Kitchen, Furniture)

COCO VOC to non-VOC

COCO VOC to non-VOC

COCO-Mix

COCO-Mix

COCO-OOD

COCO-OOD

0

Towards Open World Object Detection

Salman Hameed Khan, F. Khan, K. J. Joseph, V. Balasubramanian•Tue Mar 02 2021

This work proposes a novel computer vision problem called ORE: Open World Object Detector, which is based on contrastive clustering and energy based unknown identification, and finds that identifying and characterising unknown instances helps to reduce confusion in an incremental object detection setting.

556 0

Class-Agnostic Object Detection with Multi-modal Transformer

F. Khan, R. Anwer, Salman H. Khan, Ming Yang, Muhammad Maaz, H. Rasheed•Sun Nov 21 2021

This paper advocates that existing methods lack a top-down supervision signal governed by human-understandable semantics and demonstrates that Multi-modal Vision Transformers (MViT) trained with aligned image-text pairs can effectively bridge this gap.

117 0

Hyp-OW: Exploiting Hierarchical Structure Learning with Hyperbolic Distance Enhances Open World Object Detection

T. Doan, Sima Behpour, Wenbin He, Liangke Gou, Liu Ren•Sat Jun 24 2023

Hyp-OW is proposed, a method that learns and models hierarchical representation of known items through a SuperClass Regularizer, which allows it to effectively detect unknown objects using a similarity distance-based relabeling module.

13 0

Localized Vision-Language Matching for Open-vocabulary Object Detection

T. Brox, Sudhanshu Mittal, M. A. Bravo•Wed May 11 2022

This work proposes an open-vocabulary object detection method that, based on image-caption pairs, learns to detect novel object classes along with a given set of known classes and shows that a simple language model fits better than a large contextualized language model for detecting novel objects.

32 0

Detecting the open-world objects with the help of the Brain

Shuailei Ma, Yuefeng Wang, Ying Wei, Thomas H. Li, Peihao Chen, Zhixiang Ye, Jiaqi Fan, Enming Zhang•Mon Mar 20 2023

This paper proposes the down-weight loss function and decoupled detection structure, and leverages the VL as the ``Brain'' of the open-world detector by simply generating unknown labels, to learn novel objects beyond VL through the authors' pseudo-labeling scheme.

6 0

PROB: Probabilistic Objectness for Open World Object Detection

Serena Yeung, O. Zohar, Kuan-Chieh Jackson Wang•Thu Dec 01 2022

A novel probabilistic framework for objectness estimation is introduced, where it alternate between probability distribution estimation and objectness likelihood maximization of known objects in the embedded feature space - ultimately allowing to estimate the objectness probability of different proposals.

97 0

Revisiting Open World Object Detection

Yuqing Ma, Xianglong Liu, Xiaowei Zhao, Yifan Shen, Yixuan Qiao, Duorui Wang•Sun Jan 02 2022

This paper proposes five fundamental benchmark principles in line with the OWOD definition and constructs two OWOD benchmarks according to the principles for a fair evaluation and introduces a novel and effective OWOD framework with an auxiliary Proposal ADvisor (PAD) and a Class-specific Expelling Classifier (CEC).

72 0

UC-OWOD: Unknown-Classified Open World Object Detection

Zhi-zong Wu, Yue Lu, Xingyu Chen, Zhengxing Wu, Liwen Kang, Junzhi Yu•Fri Jul 22 2022

This work formulate the problem and devise a two-stage object detector to solve UC-OWOD, a novel OWOD problem called Unknown-Classified Open World Object Detection, which aims to detect unknown instances and classify them into different unknown classes.

75 0

OW-DETR: Open-world Detection Transformer

M. Shah, Salman Hameed Khan, F. Khan, K. J. Joseph, Sanath Narayan, Akshita Gupta•Wed Dec 01 2021

This work introduces a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection that explicitly encodes multi-scale contextual information, possesses less inductive bias, enables knowledge transfer from known classes to the unknown class and can better discriminate between unknown objects and background.

240 0

Adding a benchmark result helps the community track progress.

Open World Object Detection | State-of-the-Art