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/FIBER-B

FIBER-B

Reported on 18 benchmarks across 6 tasks · 1 paper · 15 SOTA

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

Methodology12 results

3DonDescription Detection Dataset
Intra-scenario ABS mAP· 2022-06-15
26
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
3DonDescription Detection Dataset
Intra-scenario FULL mAP· 2022-06-15
22.7
best: 22.9 (MM-Grounding-DINO)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
3DonDescription Detection Dataset
Intra-scenario PRES mAP· 2022-06-15
21.5
best: 23.7 (OFA-DOD-base)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
2D ClassificationonDescription Detection Dataset
Intra-scenario ABS mAP· 2022-06-15
26
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
2D ClassificationonDescription Detection Dataset
Intra-scenario FULL mAP· 2022-06-15
22.7
best: 22.9 (MM-Grounding-DINO)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
2D ClassificationonDescription Detection Dataset
Intra-scenario PRES mAP· 2022-06-15
21.5
best: 23.7 (OFA-DOD-base)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
2D Object DetectiononDescription Detection Dataset
Intra-scenario ABS mAP· 2022-06-15
26
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
2D Object DetectiononDescription Detection Dataset
Intra-scenario FULL mAP· 2022-06-15
22.7
best: 22.9 (MM-Grounding-DINO)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
2D Object DetectiononDescription Detection Dataset
Intra-scenario PRES mAP· 2022-06-15
21.5
best: 23.7 (OFA-DOD-base)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
16konDescription Detection Dataset
Intra-scenario ABS mAP· 2022-06-15
26
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
16konDescription Detection Dataset
Intra-scenario FULL mAP· 2022-06-15
22.7
best: 22.9 (MM-Grounding-DINO)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
16konDescription Detection Dataset
Intra-scenario PRES mAP· 2022-06-15
21.5
best: 23.7 (OFA-DOD-base)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643

Computer Vision3 results

Object DetectiononDescription Detection Dataset
Intra-scenario ABS mAP· 2022-06-15
26
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
Object DetectiononDescription Detection Dataset
Intra-scenario FULL mAP· 2022-06-15
22.7
best: 22.9 (MM-Grounding-DINO)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
Object DetectiononDescription Detection Dataset
Intra-scenario PRES mAP· 2022-06-15
21.5
best: 23.7 (OFA-DOD-base)
SOTA
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643

Natural Language Processing3 results

Phrase GroundingonFlickr30k Entities Test
R@1· uses extra data· 2022-06-15
87.4
best: 87.7 (GLIPv2)
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
Phrase GroundingonFlickr30k Entities Test
R@10· uses extra data· 2022-06-15
97.6
best: 98.1 (GLIP)
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643
Phrase GroundingonFlickr30k Entities Test
R@5· uses extra data· 2022-06-15
96.4
best: 96.9 (GLIP)
Coarse-to-Fine Vision-Language Pre-training with Fusion in the Backbone arXiv:2206.07643