uda
uda copied to clipboard
Share similar idea with CVPR 19 paper
Hi,
Very interesting work by applying the data augmentation to semi-supervised learning. But I think the idea is quite similar to our CVPR 19 paper [1], which also tries to align the original unlabelled sample and it augmented sample. Would you please cite our paper in your updated manuscript? Thanks very much.
[1] Unsupervised Embedding Learning via Invariant and Spreading Instance Feature. In CVPR 2019.
Your work is indeed related to ours though your work aims to learn representations. We'll add a citation in the future version.