Open Zzhc3321 opened 8 months ago
Hi, thank you for your attention.
A: Many of our experiments were conducted on duke, but we did notice the privacy issue. Therefore, in the version published on cvf, we deleted results that are related to duke. At the same time, we remained these results on arxiv. So they're actually two different versions. Check no-duke-version at https://openaccess.thecvf.com/content/ICCV2023/papers/Ni_Part-Aware_Transformer_for_Generalizable_Person_Re-identification_ICCV_2023_paper.pdf.
A: It's correct that DG requires a trained model to generalize to arbitrary unseen domain, so the hyper-parameters are supposed to be constant. However, the hyper-parameters only change when we use different source domains, which have nothing to do with target domains. In other words, if we use A as source, we will only train one model to generalize on E, F, G. But when applying B as source, we may try another training setting due to it's data amount and other factors. You can see similar modifications when applying different scales of training data: https://github.com/damo-cv/TransReID/issues/19#issuecomment-864552276.
A: We exhibited the best ones on our paper since the differences between best ones and final ones are not apparent. But I guess it's not rigorous enough due to the defination of DG, and to show final ones is the better. So thank you for your advice again.
Have you tried to verify the effect on other datasets. For example, there are currently three recognized protocols (Mimic Embedding via Adaptive Aggregation: Learning Generalizable Person Re identification. Adaptive Cross Domain Learning for Generalizable Person Re identification). Notably, the removal of experiments related to Duke has led to a substantial reduction in the overall number of experiments, especially the lack of experimental results on multiple source domains.
1.论文使用了duke数据集,这个数据集应该是不让使用的。 2.目前多源域行人重识别,大部分是基于新的协议展开(剔除duke)。 3.关于代码,请问为什么不同数据集要设置不同的参数,这是否符合领域泛化的要求。 4.还有代码里在保存模型参数时,有一个操作是选择最优mAP的模型保存,请问论文里使用是训练过程中最优的结果,还是最终epoch的结果。
您好,请问代码中哪里体现了不同数据集要设置不同的参数呢?我看yml里就一种设置。谢谢 @Zzhc3321
1.论文使用了duke数据集,这个数据集应该是不让使用的。 2.目前多源域行人重识别,大部分是基于新的协议展开(剔除duke)。 3.关于代码,请问为什么不同数据集要设置不同的参数,这是否符合领域泛化的要求。 4.还有代码里在保存模型参数时,有一个操作是选择最优mAP的模型保存,请问论文里使用是训练过程中最优的结果,还是最终epoch的结果。