SiamFusion issues

two questions about this improvement

1: I trained it with GOT10K and got a very low results,Is VID necessary? 2: Random noise is used in training, and pictures are input in running time.If you take...

jiaqinxu

Reference to the report of this work

I created a new architecture based on your network for my master thesis. Could you send me the reference to your thesis so I can cite your work please

bqm1111

it seems that this project is modified by got10k/siamfc 1、backbone(modified Alexnet?) (3,192)-bn-relu-(192,256)-(256,572)-bn-relu-(512,512)-bn-relu-(512,384) no layer between conv2 and conv3,why delete this bn-relu? 2、fusion(sp_noise) combined at conv1. data enhance. if combined at...

perhuaper