OpenLongTailRecognition-OLTR
OpenLongTailRecognition-OLTR copied to clipboard
zhmiao
Pytorch implementation for "Large-Scale Long-Tailed Recognition in an Open World" (CVPR 2019 ORAL)
I have downloaded ILSVRC2014 and it looks like this:  Then I untar the training set, it looks like this:  So how to arrange them? Could you give me...
Hi, I would like to ask for the plain model of Resnet10 on ImageNet_LT, how many epochs did you use? Because if I set it to 90 epochs the performance...
Hi, I am going to train on my own dataset, I changed all the data path accordingly. But when I was trying to fine-tune resnet-152, I encountered the following error...
Hi, I have read the paper and wondering what features (meta-embedding or direct feature) did you use as a face recognition embedding. Since megaface is an open set, each meta-embedding...
Thank you for the great work. I was wondering if there are correct results on the F-measure of the other models in your paper (lifted loss, range loss, etc)? I...
Hi, thanks for your great work. Could you please provide the config files for iNat18?
Why was an FC (add_fc) layer that was **not trained** in the stage I used when initializing the centroid? Why not directly use ResNet feature extraction to directly output the...
Hi, Thanks for the awesome paper and implementation. The following are the versions of files that can be downloaded from the official website of Places365 dataset (http://places2.csail.mit.edu/download.html): Data of Places365-Standard...
