Instance Segmentation on COCO 2017 (minival)
38.2APsR3-CNN (advanced)
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| R3-CNN (advanced)# Params=50,072 K, TS=Inc, Lt=3, H=1, Speed=1.0, Mem. usage=6.8 GB, Model size=384 MB2021.04 | 38.2 | — | — | — | — | — | |
| HTC# Params=77,230 K, TS=Inc, Lt=3, H=3, Speed=5.4, Mem. usage=6.8 GB, Model size=591 MB2021.04 | 36.9 | — | — | — | — | — | |
| R3-CNN (naive)# Params=43,912 K, TS=Inc, Lt=3, H=1, Speed=5.5, Mem. usage=5.9 GB, Model size=337 MB2021.04 | 36.8 | — | — | — | — | — | |
| R³-CNN (naive)# Params=43,912 K, TS=Dec, Lt=3, H=1, Speed=5.5, Mem. usage=5.9 GB, Model size=337 MB2021.04 | 36.7 | — | — | — | — | — | |
| Mask (3x)# Params=44,170 K, TS=-, Lt=1, H=1, Speed=5.4, Mem. usage=4.4 GB, Model size=339 MB2021.04 | 35.5 | — | — | — | — | — | |
| Mask (1x)# Params=44,170 K, TS=-, Lt=1, H=1, Speed=11.5, Mem. usage=4.4 GB, Model size=339 MB2021.04 | 34.7 | — | — | — | — | — | |
| GC-netBackbone=r50-FPN2020.04 | 20.4 | 35.9 | 58.5 | 38 | 39.4 | 49 | |
| GC-net + GROIEBackbone=r50-FPN2020.04 | 20.2 | 37.2 | 59.3 | 39.8 | 41 | 51.2 | |
| Mask R-CNN + GROIEBackbone=r50-FPN2020.04 | 19.1 | 35.8 | 57.1 | 38 | 39 | 48.7 | |
| Mask R-CNNBackbone=r50-FPN2020.04 | 18 | 34.1 | 55.5 | 36.1 | 37.6 | 46.7 |