Recent searches
Search options
How robust are unsupervised representation learning methods (e.g. SSL) to distirbution shift compared to supervised learning?
𝐒𝐡𝐨𝐫𝐭 𝐚𝐧𝐬𝐰𝐞𝐫: Quite!
𝐋𝐨𝐧𝐠 𝐚𝐧𝐬𝐰𝐞𝐫: Our #ICLR2023 paper http://arxiv.org/pdf/2206.08871.pdf
Joint work with Imant Daunhawer & Amartya Sanyal @amartya
So why the discrepency in performance on synthetic vs. realistic datasets? We observe that the former features more extreme distribution shift, while the latter features subtle, nuaunced shifts.
Are unsupervised learning better at handling extreme distribution shift?
(4/n)