Hi authors, thanks for this amazing work! I have some questions about the performance difference in different version of this paper on arxiv. In the first version, the performance of R-50 is 34.4, and in the final version, the performance is 36.2. Could you help explain what modification you make leads to this performance boost? Thanks!
Hi authors, thanks for this amazing work! I have some questions about the performance difference in different version of this paper on arxiv. In the first version, the performance of R-50 is 34.4, and in the final version, the performance is 36.2. Could you help explain what modification you make leads to this performance boost? Thanks!