search

xiaomengyc / SPG

(ECCV2018) Self-produced Guidance for Weakly-supervised Object Localization
https://arxiv.org/abs/1807.08902
MIT License
146 stars 25 forks source link

Localization metric #10

Open won-bae opened 4 years ago

won-bae commented 4 years ago

Hi, Thank you for sharing the code.

I have checked your code and realized there is no metric to measure top1-localization accuracy. Also, val_list.txt for both cub and imagenet only contain class label not bounding box information. Can you please explain how you evaluate the performance of top1-loc? For example, where the bounding box information is or where the top1-loc metric is measured. Thank you in advance!