This is the official PyTorch implementation of the paper "TransFG: A Transformer Architecture for Fine-grained Recognition" (Ju He, Jie-Neng Chen, Shuai Liu, Adam Kortylewski, Cheng Yang, Yutong Bai, Changhu Wang, Alan Yuille).
I attempted to verify the functionality of the PSM module and noticed that incorporating only the PSM module into ViT didn't seem to enhance performance. Could you please let me know if there is a transfg model weights trained on CUB?
I attempted to verify the functionality of the PSM module and noticed that incorporating only the PSM module into ViT didn't seem to enhance performance. Could you please let me know if there is a transfg model weights trained on CUB?