Open Vocabulary Object Detection

Open-vocabulary detection (OVD) aims to generalize beyond the limited number of base classes labeled during the training phase. The goal is to detect novel classes defined by an unbounded (open) vocabulary at inference.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 51–60 of 145 papers

Title	Date	Tasks	Status	Hype	Score
MoCaE: Mixture of Calibrated Experts Significantly Improves Object Detection	Sep 26, 2023	Instance SegmentationMixture-of-Experts	CodeCode Available	1	5
Learning to Prompt for Open-Vocabulary Object Detection with Vision-Language Model	Mar 28, 2022	image-classificationImage Classification	CodeCode Available	1	5
DART: An Automated End-to-End Object Detection Pipeline with Data Diversification, Open-Vocabulary Bounding Box Annotation, Pseudo-Label Review, and Model Training	Jul 12, 2024	Image GenerationObject	CodeCode Available	1	5
Comprehensive Multi-Modal Prototypes are Simple and Effective Classifiers for Vast-Vocabulary Object Detection	Dec 23, 2024	object-detectionObject Detection	CodeCode Available	1	5
DST-Det: Simple Dynamic Self-Training for Open-Vocabulary Object Detection	Oct 2, 2023	Novel Object DetectionObject	CodeCode Available	1	5
Learning Object-Language Alignments for Open-Vocabulary Object Detection	Nov 27, 2022	Objectobject-detection	CodeCode Available	1	5
Query3D: LLM-Powered Open-Vocabulary Scene Segmentation with Language Embedded 3D Gaussian	Aug 7, 2024	Autonomous Drivingobject-detection	CodeCode Available	1	5
OVMR: Open-Vocabulary Recognition with Multi-Modal References	Jun 7, 2024	Open Vocabulary Object Detection	CodeCode Available	1	5
CORA: Adapting CLIP for Open-Vocabulary Detection with Region Prompting and Anchor Pre-Matching	Mar 23, 2023	Described Object Detectionobject-detection	CodeCode Available	1	5
Exploiting Unlabeled Data with Vision and Language Models for Object Detection	Jul 18, 2022	Objectobject-detection	CodeCode Available	1	5

Show:10 25 50

← PrevPage 6 of 15Next →

All datasets MSCOCO LVIS v1.0 Objects365 OpenImages-v4

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	Cooperative Foundational Models	AP 0.5	50.3	—	Unverified
2	DE-ViT	AP 0.5	50	—	Unverified
3	Yolov8-nano	AP 0.5	47.2	—	Unverified
4	DITO	AP 0.5	46.1	—	Unverified
5	OV-DQUO(RN50x4)	AP 0.5	45.6	—	Unverified
6	LP-OVOD (OWL-ViT Proposals)	AP 0.5	44.9	—	Unverified
7	CLIPSelf	AP 0.5	44.3	—	Unverified
8	CORA+	AP 0.5	43.1	—	Unverified
9	BARON	AP 0.5	42.7	—	Unverified
10	SIA-OVD (RN50x4)	AP 0.5	41.9	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	LaMI-DETR	AP novel-LVIS base training	43.4	—	Unverified
2	DITO	AP novel-LVIS base training	40.4	—	Unverified
3	OV-DQUO(ViT-L/14)	AP novel-LVIS base training	39.3	—	Unverified
4	CoDet (EVA02-L)	AP novel-LVIS base training	37	—	Unverified
5	CLIPSelf	AP novel-LVIS base training	34.9	—	Unverified
6	OVMR	AP novel-LVIS base training	34.4	—	Unverified
7	DE-ViT	AP novel-LVIS base training	34.3	—	Unverified
8	CFM-ViT	AP novel-LVIS base training	33.9	—	Unverified
9	CLIM (RN50x64)	AP novel-LVIS base training	32.3	—	Unverified
10	RO-ViT	AP novel-LVIS base training	32.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Object-Centric-OVD	mask AP50	22.3	—	Unverified
2	ViLD	mask AP50	18.2	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	Object-Centric-OVD	mask AP50	42.9	—	Unverified
2	Detic	mask AP50	42.2	—	Unverified