Baseline performance on CAVIAR

[ForeUP]

Thank you for your excellent work.

I am interested in knowing how you produced the results using the Baseline model on CAVIAR.

Looking forward to your response!

[Yukun-Huang]

Thanks for your attention! The CAVIAR and MLR-VIPeR datasets are too small to get reliable results. Using fewer iteration steps (e.g., 1/3 of the original number of steps) may avoid overfitting and improve performance.

[ForeUP]

I tested it every epoch during training, and the best results I obtained were:

2023-08-19 23:45:27,157 reid_baseline.train INFO: ----------
2023-08-19 23:45:28,445 reid_baseline.train INFO: Validation Results - Epoch: 30
2023-08-19 23:45:28,445 reid_baseline.train INFO: mAP: 35.7%
2023-08-19 23:45:28,445 reid_baseline.train INFO: CMC curve, Rank-1 :42.8%
2023-08-19 23:45:28,446 reid_baseline.train INFO: CMC curve, Rank-5 :66.4%
2023-08-19 23:45:28,446 reid_baseline.train INFO: CMC curve, Rank-10 :78.4%

Could you please provide more details or share the weights file along with the dataset source file?
Thank you very much for your response!