features about rerank

[zengkaiwei]

Usually rerank is used in one dataset,but in your rerank.py you rerank source feature with target feature? Why? Or my understanding is fault? At this moment, what's the mean of your e_dist and r_dist? Is it still distence between each sample in target datasets?

[xiaobaoli15]

I have also the same question.

[tiancity-NJU]

same question too

[OasisYang]

Sorry for the late reply, I was really busy. Your understanding is right, we use re-rank between source feature and target feature. The motivation is to obtain a better re-rank result by the knowledge of source dataset. (since the model can achieve pretty good performance on source dataset).
e_dist is the euclidean distance among samples in a target dataset. r_dist is the distance after re-ranking.
Hope this can solve your problem.

[JingweiZhang12]

Did you try to use the original dist rather than source dist? What's the performance compared to the current source dist?