Tried to tweak code to work on deepfashion1 INSHOP dataset, which results was shown on in original paper.
Note: Didnt finish tweaking the code to get the numbers from original paper.
Pytorch Implementation of paper Attention-based Ensemble for Deep Metric Learning
Major difference from the paper: attention maps are not followed by a sigmoid activation function and minmax norm are used instead.
The weighted sampling module code is copied from suruoxi/DistanceWeightedSampling
performance on Stanford Cars 196: 71.4% recall@1 86.9% recall@4 (8 attentions and size of each embedding is 64)
transform attention map: att_maps = sign(att_maps) * sqrt(abs(att_maps)) before normalizing. (Motivated by tau-yihouxiang/WSDAN)
Will update here if I got better validation performance