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/GROUNDHOG

GROUNDHOG

Reported on 16 benchmarks across 2 tasks · 1 paper

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

Computer Vision16 results

Instance SegmentationonRefCoCo val
Overall IoU· uses extra data· 2024-02-26
78.5
best: 85.41 (DeRIS-L)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Instance SegmentationonPhraseCut
Mean IoU· 2024-02-26
54.5
best: 61.3 (GLIPv2)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Instance SegmentationonRefCOCOg-test
Overall IoU· uses extra data· 2024-02-26
74.6
best: 80.54 (UniLSeg-100)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Instance SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2024-02-26
70.5
best: 79.4 (MLCD-Seg-7B)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Instance SegmentationonRefCOCO+ test B
Overall IoU· uses extra data· 2024-02-26
64.9
best: 75.6 (MLCD-Seg-7B)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Instance SegmentationonRefCOCO+ testA
Overall IoU· uses extra data· 2024-02-26
75
best: 83.5 (HyperSeg)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Instance SegmentationonRefCOCOg-val
Overall IoU· uses extra data· 2024-02-26
74.1
best: 79.9 (MLCD-Seg-7B)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Instance SegmentationongRefCOCO
gIoU· uses extra data· 2024-02-26
66.7
best: 77.67 (DeRIS-L)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationonRefCoCo val
Overall IoU· uses extra data· 2024-02-26
78.5
best: 85.41 (DeRIS-L)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationonPhraseCut
Mean IoU· 2024-02-26
54.5
best: 61.3 (GLIPv2)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationonRefCOCOg-test
Overall IoU· uses extra data· 2024-02-26
74.6
best: 80.54 (UniLSeg-100)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2024-02-26
70.5
best: 79.4 (MLCD-Seg-7B)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationonRefCOCO+ test B
Overall IoU· uses extra data· 2024-02-26
64.9
best: 75.6 (MLCD-Seg-7B)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationonRefCOCO+ testA
Overall IoU· uses extra data· 2024-02-26
75
best: 83.5 (HyperSeg)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationonRefCOCOg-val
Overall IoU· uses extra data· 2024-02-26
74.1
best: 79.9 (MLCD-Seg-7B)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846
Referring Expression SegmentationongRefCOCO
gIoU· uses extra data· 2024-02-26
66.7
best: 77.67 (DeRIS-L)
GROUNDHOG: Grounding Large Language Models to Holistic Segmentation arXiv:2402.16846