search

uber-research / UPSNet

UPSNet: A Unified Panoptic Segmentation Network
Other
649 stars 119 forks source link

what‘’s the performance compared with Mask RCNN on object detection? #47

Open scut-salmon opened 5 years ago

scut-salmon commented 5 years ago

Hi, I find that UPSNet mainly add an semantic segmentation head to mask RCNN, I wonder what's the performance of UPSNet on object detection(or instance segmentation). Can I use it to improve my object detection MAP? Sorry but I didn't find this discuss in your paper.

I would be appreciated if you could give me some advice, thanks.

kevinj22 commented 5 years ago

Running the eval code given with the trained weights for the 101 resnet:

BBOX:

2019-06-24 15:10:53,159 | base_dataset.py | line 718: ~~ Summary metrics ~~ Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.443 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.658 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.482 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.267 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.480 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.590 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.347 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.541 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.566 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.378 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.604 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.710

SEGM:

2019-06-24 15:11:44,648 | base_dataset.py | line 718: ~~ Summary metrics ~~ Average Precision (AP) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.389 Average Precision (AP) @[ IoU=0.50 | area= all | maxDets=100 ] = 0.621 Average Precision (AP) @[ IoU=0.75 | area= all | maxDets=100 ] = 0.413 Average Precision (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.184 Average Precision (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.416 Average Precision (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.584 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 1 ] = 0.316 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets= 10 ] = 0.481 Average Recall (AR) @[ IoU=0.50:0.95 | area= all | maxDets=100 ] = 0.501 Average Recall (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.300 Average Recall (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.539 Average Recall (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.674