Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟭𝟳𝟲 Computer Vision Learning 𝗦𝗖𝗔𝗡: Learning to Classify Images without Labels by 𝗘𝗧𝗛 𝗭𝘂𝗿𝗶𝗰𝗵/𝗖𝗩𝗟, 𝗧𝗥𝗔𝗖𝗘 Follow me for a similar post:  🇮🇳 Ashish Patel Interesting Facts : 🔸 This is a paper in ECCV2020 with over 44 citations. ------------------------------------------------------------------- 𝗔𝗺𝗮𝘇𝗶𝗻𝗴 𝗥𝗲𝘀𝗲𝗮𝗿𝗰𝗵 : https://lnkd.in/eBfJXXZ Code : https://lnkd.in/exdVGUQ ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 🔸 Is it possible to automatically classify images without the use of ground-truth annotations? Or when even the classes themselves, are not a priori known? These remain important, and open questions in computer vision. Several approaches have tried to tackle this problem in an end-to-end fashion. 🔸 In this paper, Authors deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task from representation learning is employed to obtain semantically meaningful features. Second, we use the obtained features as a prior in a learnable clustering approach. 🔸In doing so, Authors remove the ability for cluster learning to depend on low-level features, which is present in current end-to-end learning approaches. Experimental evaluation shows that we outperform state-of-the-art methods by huge margins, in particular + 26.9 % on CIFAR10, + 21.5 % on CIFAR100-20 and + 11.7 % on STL10 in terms of classification accuracy. #computervision #artificialintelligence #innovation