durandtibo / wildcat.pytorch

PyTorch implementation of "WILDCAT: Weakly Supervised Learning of Deep ConvNets for Image Classification, Pointwise Localization and Segmentation", CVPR 2017
MIT License
267 stars 61 forks source link

Not learning different modalities? #11

Open jtrammell-dla opened 5 years ago

jtrammell-dla commented 5 years ago

My experiments using this code so far (using the settings suggested in the readme) seem to be learning, and producing good classification and localization results, but the separate output layers are not learning different modalities as suggested by the paper. All 8 layers appear to be more or less identical to each other. Am I missing something?