Tasks SotA Datasets Papers Methods Submit About

Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable Benchmarks All SotA Datasets Papers Methods

Community

Submit Results About

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Models/Detic

Detic

Reported on 24 benchmarks across 6 tasks · 1 paper · 12 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology16 results

3DonOpenImages-v4
AP 0.5· 2022-01-07
42.2
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
3DonOpenImages-v4
mask AP50· 2022-01-07
42.2
best: 42.9 (Object-Centric-OVD)
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D ClassificationonOpenImages-v4
AP 0.5· 2022-01-07
42.2
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D ClassificationonOpenImages-v4
mask AP50· 2022-01-07
42.2
best: 42.9 (Object-Centric-OVD)
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D Object DetectiononOpenImages-v4
AP 0.5· 2022-01-07
42.2
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D Object DetectiononOpenImages-v4
mask AP50· 2022-01-07
42.2
best: 42.9 (Object-Centric-OVD)
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
16konOpenImages-v4
AP 0.5· 2022-01-07
42.2
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
16konOpenImages-v4
mask AP50· 2022-01-07
42.2
best: 42.9 (Object-Centric-OVD)
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
3DonLVIS v1.0
AP novel-LVIS base training· uses extra data· 2022-01-07
17.8
best: 43.4 (LaMI-DETR)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
3DonMSCOCO
AP 0.5· 2022-01-07
27.8
best: 50.3 (Cooperative Foundational Models)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D ClassificationonLVIS v1.0
AP novel-LVIS base training· uses extra data· 2022-01-07
17.8
best: 43.4 (LaMI-DETR)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D ClassificationonMSCOCO
AP 0.5· 2022-01-07
27.8
best: 50.3 (Cooperative Foundational Models)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D Object DetectiononLVIS v1.0
AP novel-LVIS base training· uses extra data· 2022-01-07
17.8
best: 43.4 (LaMI-DETR)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
2D Object DetectiononMSCOCO
AP 0.5· 2022-01-07
27.8
best: 50.3 (Cooperative Foundational Models)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
16konLVIS v1.0
AP novel-LVIS base training· uses extra data· 2022-01-07
17.8
best: 43.4 (LaMI-DETR)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
16konMSCOCO
AP 0.5· 2022-01-07
27.8
best: 50.3 (Cooperative Foundational Models)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605

Computer Vision8 results

Object DetectiononOpenImages-v4
AP 0.5· 2022-01-07
42.2
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
Object DetectiononOpenImages-v4
mask AP50· 2022-01-07
42.2
best: 42.9 (Object-Centric-OVD)
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
Open Vocabulary Object DetectiononOpenImages-v4
AP 0.5· 2022-01-07
42.2
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
Open Vocabulary Object DetectiononOpenImages-v4
mask AP50· 2022-01-07
42.2
best: 42.9 (Object-Centric-OVD)
SOTA
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
Object DetectiononLVIS v1.0
AP novel-LVIS base training· uses extra data· 2022-01-07
17.8
best: 43.4 (LaMI-DETR)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
Object DetectiononMSCOCO
AP 0.5· 2022-01-07
27.8
best: 50.3 (Cooperative Foundational Models)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
Open Vocabulary Object DetectiononLVIS v1.0
AP novel-LVIS base training· uses extra data· 2022-01-07
17.8
best: 43.4 (LaMI-DETR)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605
Open Vocabulary Object DetectiononMSCOCO
AP 0.5· 2022-01-07
27.8
best: 50.3 (Cooperative Foundational Models)
Detecting Twenty-thousand Classes using Image-level Supervision arXiv:2201.02605