HIPIE

Reported on 5 benchmarks across 3 tasks · 1 paper · 4 SOTA

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

Computer Vision5 results

Instance SegmentationonRefCoCo val
Overall IoU· uses extra data· 2023-07-03
82.8
best: 85.41 (DeRIS-L)
SOTA
Hierarchical Open-vocabulary Universal Image Segmentation arXiv:2307.00764
Instance SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2023-07-03
73.9
best: 79.4 (MLCD-Seg-7B)
SOTA
Hierarchical Open-vocabulary Universal Image Segmentation arXiv:2307.00764
Referring Expression SegmentationonRefCoCo val
Overall IoU· uses extra data· 2023-07-03
82.8
best: 85.41 (DeRIS-L)
SOTA
Hierarchical Open-vocabulary Universal Image Segmentation arXiv:2307.00764
Referring Expression SegmentationonRefCOCO+ val
Overall IoU· uses extra data· 2023-07-03
73.9
best: 79.4 (MLCD-Seg-7B)
SOTA
Hierarchical Open-vocabulary Universal Image Segmentation arXiv:2307.00764
Zero Shot SegmentationonSegmentation in the Wild
Mean AP· 2023-07-03
41.6
best: 49.6 (Grounded HQ-SAM)
Hierarchical Open-vocabulary Universal Image Segmentation arXiv:2307.00764