Mean Shift for Self-Supervised Learning
Links to Fileshttps://www.csee.umbc.edu/~hpirsiav/papers/MeanShift.pdf
MetadataShow full item record
Type of Work15 pages
Citation of Original PublicationSoroush Abbasi Koohpayegani, Ajinkya Tejankar and Hamed Pirsiavash, Mean Shift for Self-Supervised Learning, https://www.csee.umbc.edu/~hpirsiav/papers/MeanShift.pdf
RightsThis item is likely protected under Title 17 of the U.S. Copyright Law. Unless on a Creative Commons license, for uses protected by Copyright Law, contact the copyright holder or the author.
Most recent self-supervised learning (SSL) algorithms learn features by contrasting between instances of images or by clustering the images and then contrasting between the image clusters. We introduce a simple mean-shift algorithm that learns representations by grouping images together without contrasting between them or adopting much of prior on the structure of the clusters. We simply “shift” the embedding of each image to be close to the “mean” of its neighbors. Since in our setting, the closest neighbor is always another augmentation of the same image, our model will be identical to BYOL when using only one nearest neighbor instead of 5 as used in our experiments. Our model achieves 72.4% on ImageNet linear evaluation with ResNet50 at 200 epochs outperforming BYOL.