search

zhufengx / SRN_multilabel

143 stars 39 forks source link

problem about calculating top3 precision and recall #1

Closed jiqiujia closed 6 years ago

jiqiujia commented 7 years ago

From your paper, it seems that your do thresholding before calculating top3 precision and recall. However, the compared methods didn't seem to do that. I doubt if it is acceptable to do thresholding before calculating top3 precision and recall. Please clarify this, thanks.

zhufengx commented 7 years ago

@jiqiujia

Thank you for the question!

We only did thresholding on MS-COCO dataset, following "CNN-RNN: A Unified Framework for Multi-label Image Classification, CVPR 2016"

Please refer to paragraph 2 of section 4.3 of the above paper: "Since the number of the objects per image varies considerably in this dataset, we do not set the minimum length of the prediction path during beam search"

jiqiujia commented 7 years ago

Thanks for your quick reply. I understand now.

jiqiujia commented 7 years ago

Besides, I would like to say this is really an awesome design. Could you share me with some experience of the designation of neural network architecture?

zhufengx commented 7 years ago

@jiqiujia

Thank you for your comments! For this work, the crucial parts are "gating operation (element-wise multiplication and sum pooling)" and "spatial softmax". These are ideas borrowed from widely used attention mechanism with some adaption to the multi-label problem. The left parts are a lot of experiments.

jiqiujia commented 7 years ago

Thanks! Your answer help me to have a deeper understanding of this work!