What about the ablation study of AGW on visible-infrared Re-ID?

mangye16 / Cross-Modal-Re-ID-baseline

Pytorch Code for Cross-Modality Person Re-Identification (Visible Thermal/Infrared Re-ID)

MIT License

336 stars 71 forks source link

What about the ablation study of AGW on visible-infrared Re-ID? #20

Open mouxingyang opened 3 years ago

mouxingyang commented 3 years ago

Hi~ It is a nice job. The proposed WRT loss seems to be the improved version of the original Triplet loss. Did you carry out any ablation studies on the proposed AGW baseline for cross-modality visible-infrared Re-ID? If so, how much performance improved by the WRT comparing to the triplet?

Thanks

mouxingyang commented 3 years ago

Hi~ I have tried the recommend code using triplet loss and the proposed wrt loss, respectively. However, the one with triplet loss exceeds that with wrt loss by ~7% and ~2.7 in terms of the rank-1 under the POOL and FC setting, respectively.