NP-RepMet issues

loss in the code is not the same as in the paper

1

Hi, thank for the nice work and the idea of restoring negative information is quite inspiring. However, I find that the loss in the code is not the same as...

kyrawu327

Config Files for Reproducing the Table-3 Results in the Paper on PASCAL VOC Dataset

It seems that the config files are only for experiments on the ImageNet-LOC dataset, but I would like to reproduce the results on the PASCAL VOC dataset. Could you provide...

II-Matto

The result of COCO

1

Dear Authors, Do you evaluate your method on COCO dataset? Thank you.

AmingWu

Novel samples for finetuning

1

Hello, thanks for you nice paper and released source code. I wonder how did you select K-shot samples in Pascal VOC dataset for novel classes. Is it same with FSRW(ICCV...

mandal4