Tasks
SotA
Datasets
Papers
Methods
Submit
About
SotA
/
Methodology
/
2D Object Detection
/
LVIS v1.0 minival
2D Object Detection on LVIS v1.0 minival
Metric: AP (higher is better)
Leaderboard
Dataset
Loading chart...
Results
Submit a result
Hide augmentations
Export CSV
#
Model
↕
AP
▼
Augmentations
Paper
Date
↕
Code
1
CP-DETR-Pro(without LVIS data)
58.2
Yes
CP-DETR: Concept Prompt Guide DETR Toward Strong...
2024-12-13
-
2
Grounding DINO 1.6 Pro (without LVIS data)
57.7
Yes
Grounding DINO 1.5: Advance the "Edge" of Open-S...
2024-05-16
Code
3
Grounding DINO 1.5 Pro (without LVIS data)
55.7
Yes
Grounding DINO 1.5: Advance the "Edge" of Open-S...
2024-05-16
Code
4
OWLv2 (OWL-ST+FT)
51.3
Yes
Scaling Open-Vocabulary Object Detection
2023-06-16
Code
5
MQ-GLIP-L
43.4
Yes
Multi-modal Queried Object Detection in the Wild
2023-05-30
Code
6
OV-DINO-T (without LVIS data, swin tiny)
40.1
Yes
OV-DINO: Unified Open-Vocabulary Detection with ...
2024-07-10
Code
7
GLIP-L
37.3
Yes
Grounded Language-Image Pre-training
2021-12-07
Code
8
YOLO-World-L
35.4
Yes
YOLO-World: Real-Time Open-Vocabulary Object Det...
2024-01-30
Code
9
GroundingDINO-L
33.9
Yes
Grounding DINO: Marrying DINO with Grounded Pre-...
2023-03-09
Code
10
MQ-GLIP-T
30.4
Yes
Multi-modal Queried Object Detection in the Wild
2023-05-30
Code
11
MQ-GroundingDINO-T
30.2
Yes
Multi-modal Queried Object Detection in the Wild
2023-05-30
Code