why SOLOv2 speed slower than MaskRCNN in paper?

[lucasjinreal]

SOLOv2 becomes slowest model in your papers, is that really? But as SOLOv2 official paper claims it should faster than most instance segmentation methods, at least compare with MaskRCNN.

[hujiecpp]

SOLOv2 becomes slowest model in your papers, is that really? But as SOLOv2 official paper claims it should faster than most instance segmentation methods, at least compare with MaskRCNN.

Hi @jinfagang , We are sorry that the running time of SOLOv2 in our paper is WRONG ... as we list the whole testing time of SOLOv2 (based on mmdet) including images-reading, post-processing, etc.

The pure running time of SOLOv2 on a single V100 GPU is (as shown in this page): 54ms (Res50) / 66ms (Res101).

The pure running time of SOLOv2 on a single 1080Ti GPU is (we re-run the code in this page): ～63ms (Res50) / ～84ms(Res101).

Thanks for indicting this issue and we will update the paper as soon as possible.

[lucasjinreal]

@hujiecpp that make more sense. Actually I hope ISTR to be more faster, if it's accurate and e2e easy to deploy. What's the fastest model currently ISTR can achieve?

[hujiecpp]

Currently, the fastest model is still ISTR-Res50 as I am now lacking of GPUs to train new models with ISTR. (Orz I plan to implement ISTR with mobilenet / vovnet backbone like centermask2.

[lucasjinreal]

@hujiecpp Does LSTR also requires RoiAlign layer?

[hujiecpp]

@jinfagang yes