Learning To Classify Images Without Labels (Paper Explained)

How do you learn labels without labels? How do you classify images when you don't know what to classify them into? This paper investigates a new combination of representation learning, clustering, and self-labeling in order to group visually similar images together - and achieves surprisingly high accuracy on benchmark datasets. OUTLINE: 0:00 - Intro & High-level Overview 2:15 - Problem Statement 4:50 - Why naive Clustering does not work 9:25 - Representation Learning 13:40 - Nearest-neighbor-based Clustering 28:00 - Self-Labeling 32:10 - Experiments 38:20 - ImageNet Experiments 41:00 - Overclustering Paper: https://ift.tt/3eQqHCd Code: https://ift.tt/2MpCJWP Abstract: 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, we 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, we 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. Furthermore, results on ImageNet show that our approach is the first to scale well up to 200 randomly selected classes, obtaining 69.3% top-1 and 85.5% top-5 accuracy, and marking a difference of less than 7.5% with fully-supervised methods. Finally, we applied our approach to all 1000 classes on ImageNet, and found the results to be very encouraging. The code will be made publicly available. Authors: Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool Links: YouTube: https://www.youtube.com/c/yannickilcher Twitter: https://twitter.com/ykilcher BitChute: https://ift.tt/38iX6OV Minds: https://ift.tt/37igBpB