𝗗𝗮𝘆-𝟮𝟱𝟳 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 𝗔 𝗦𝘂𝗿𝘃𝗲𝘆 𝗼𝗻 𝗖𝗿𝗼𝘀𝘀-𝗱𝗼𝗺𝗮𝗶𝗻 𝗖𝗼𝗻𝘁𝗿𝗮𝘀𝘁𝗶𝘃𝗲 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 for Unsupervised Domain Adaptation by Fudan University Follow me for a similar post: 🇮🇳 Ashish Patel Interesting Facts : 🔸 This paper is published arxiv 2021. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eJFUj-hg ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labelled source domain to a different unlabeled target domain. Most existing UDA methods learn domain-invariant feature representations by minimizing feature distances across domains. 🔸 In this work, we build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets. Exploring the same set of categories shared by both domains, we introduce a simple yet effective framework CDCL, for domain alignment. 🔸 In particular, given an anchor image from one domain, we minimize its distances to cross-domain samples from the same class relative to those from different categories. Since target labels are unavailable, we use a clustering-based approach with carefully initialized centres to produce pseudo labels. 🔸 In addition, we demonstrate that CDCL is a general framework and can be adapted to the data-free setting, where the source data are unavailable during training, with minimal modification. We conduct experiments on two widely used domain adaptation benchmarks, i.e., Office-31 and VisDA-2017, and demonstrate that CDCL achieves state-of-the-art performance on both datasets. #computervision #artificialintelligence #machinelearning