Unsupervised Representation Learning by Predicting Image Rotations
Spyros Gidaris, Praveer Singh, Nikos Komodakis University Paris-Est, LIGM Ecole des Ponts ParisTech
Abstract
Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manually labeled data, which is both expensive and impractical to scale. Therefore, unsupervised semantic feature learning, i.e., learning without requiring manual annotation effort, is of crucial importance in order to successfully harvest the vast amount of visual data that are available today. In our work we propose to learn image features by training ConvNets to recognize the 2d rotation that is applied to the image that it gets as input. We demonstrate both qualitatively and quantitatively that this apparently simple task actually provides a very powerful supervisory signal for semantic feature learning. We exhaustively evaluate our method in various unsupervised feature learning benchmarks and we exhibit in all of them state-of-the-art performance. Specifically, our results on those benchmarks demonstrate dramatic improvements w.r.t. prior state-of-the-art approaches in unsupervised repres
中文速览
让卷积神经网络（ConvNet）在没有人工标注的情况下学到有用的图像特征，一直是计算机视觉领域的核心难题。这篇论文提出了一个出人意料简单的自监督学习方法：把图像随机旋转0°、90°、180°或270°，然后让网络去预测旋转了多少角度——这个"猜旋转"的任务不需要任何人工标签，却逼着网络去理解图像里有什么物体、它们长什么样、朝哪个方向，从而学到丰富的语义特征。研究者在CIFAR-10、ImageNet、PASCAL VOC检测与分割等多个基准上全面测试，结果显示该方法（称为RotNet）大幅超越此前所有无监督方法，例如在PASCAL VOC 2007目标检测任务上，无监督预训练的AlexNet达到54.4% mAP，与有监督预训练仅差2.4个百分点。这项工作的意义在于：它用极低的实现成本和极强的可扩展性，显著缩小了无监督与有监督特征学习之间长期存在的性能鸿沟，为在海量无标注图像上训练强大视觉模型提供了一条切实可行的路径。
原文 arXiv:1803.07728;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1803.07728v1