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/RO-ViT

RO-ViT

Reported on 18 benchmarks across 7 tasks · 1 paper · 6 SOTA

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

Miscellaneous12 results

Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@1· 2023-05-11
92.1
best: 98.8 (X2-VLM (large))
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@10· 2023-05-11
99.7
best: 100 (X2-VLM (large))
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonFlickr30k
Image-to-text R@5· 2023-05-11
99.4
best: 100 (X2-VLM (large))
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@1· 2023-05-11
80.7
best: 93.3 (ERNIE-ViL 2.0)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@10· 2023-05-11
97.7
best: 99.8 (ERNIE-ViL 2.0)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonFlickr30k
Text-to-image R@5· 2023-05-11
96.1
best: 99.5 (M2-Encoder)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@1· 2023-05-11
68.9
best: 84.8 (BEiT-3)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@10· 2023-05-11
92.2
best: 98.5 (X2-VLM (large))
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonCOCO 2014
Image-to-text R@5· 2023-05-11
87.8
best: 96.5 (X2-VLM (large))
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@1· 2023-05-11
51.8
best: 68 (VAST)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@10· 2023-05-11
83
best: 92.8 (VAST)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Image Retrieval with Multi-Modal QueryonCOCO 2014
Text-to-image R@5· 2023-05-11
75
best: 92.8 (BEiT-3)
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011

Methodology4 results

3DonLVIS v1.0
AP novel-LVIS base training· 2023-05-11
32.1
best: 43.4 (LaMI-DETR)
SOTA
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
2D ClassificationonLVIS v1.0
AP novel-LVIS base training· 2023-05-11
32.1
best: 43.4 (LaMI-DETR)
SOTA
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
2D Object DetectiononLVIS v1.0
AP novel-LVIS base training· 2023-05-11
32.1
best: 43.4 (LaMI-DETR)
SOTA
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
16konLVIS v1.0
AP novel-LVIS base training· 2023-05-11
32.1
best: 43.4 (LaMI-DETR)
SOTA
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011

Computer Vision2 results

Object DetectiononLVIS v1.0
AP novel-LVIS base training· 2023-05-11
32.1
best: 43.4 (LaMI-DETR)
SOTA
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011
Open Vocabulary Object DetectiononLVIS v1.0
AP novel-LVIS base training· 2023-05-11
32.1
best: 43.4 (LaMI-DETR)
SOTA
Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers arXiv:2305.07011