%0 Generic %1 henaff2019dataefficient %A Hénaff, Olivier J. %A Razavi, Ali %A Doersch, Carl %A Eslami, S. M. Ali %A Oord, Aaron van den %D 2019 %K backbone loss oneshot semisup unsup %T Data-Efficient Image Recognition with Contrastive Predictive Coding %U http://arxiv.org/abs/1905.09272 %X Large scale deep learning excels when labeled images are abundant, yet data-efficient learning remains a longstanding challenge. While biological vision is thought to leverage vast amounts of unlabeled data to solve classification problems with limited supervision, computer vision has so far not succeeded in this `semi-supervised' regime. Our work tackles this challenge with Contrastive Predictive Coding, an unsupervised objective which extracts stable structure from still images. The result is a representation which, equipped with a simple linear classifier, separates ImageNet categories better than all competing methods, and surpasses the performance of a fully-supervised AlexNet model. When given a small number of labeled images (as few as 13 per class), this representation retains a strong classification performance, outperforming state-of-the-art semi-supervised methods by 10% Top-5 accuracy and supervised methods by 20%. Finally, we find our unsupervised representation to serve as a useful substrate for image detection on the PASCAL-VOC 2007 dataset, approaching the performance of representations trained with a fully annotated ImageNet dataset. We expect these results to open the door to pipelines that use scalable unsupervised representations as a drop-in replacement for supervised ones for real-world vision tasks where labels are scarce.

@misc{henaff2019dataefficient, abstract = {Large scale deep learning excels when labeled images are abundant, yet data-efficient learning remains a longstanding challenge. While biological vision is thought to leverage vast amounts of unlabeled data to solve classification problems with limited supervision, computer vision has so far not succeeded in this `semi-supervised' regime. Our work tackles this challenge with Contrastive Predictive Coding, an unsupervised objective which extracts stable structure from still images. The result is a representation which, equipped with a simple linear classifier, separates ImageNet categories better than all competing methods, and surpasses the performance of a fully-supervised AlexNet model. When given a small number of labeled images (as few as 13 per class), this representation retains a strong classification performance, outperforming state-of-the-art semi-supervised methods by 10% Top-5 accuracy and supervised methods by 20%. Finally, we find our unsupervised representation to serve as a useful substrate for image detection on the PASCAL-VOC 2007 dataset, approaching the performance of representations trained with a fully annotated ImageNet dataset. We expect these results to open the door to pipelines that use scalable unsupervised representations as a drop-in replacement for supervised ones for real-world vision tasks where labels are scarce.}, added-at = {2019-07-08T21:44:06.000+0200}, author = {Hénaff, Olivier J. and Razavi, Ali and Doersch, Carl and Eslami, S. M. Ali and Oord, Aaron van den}, biburl = {https://www.bibsonomy.org/bibtex/2f958ff01a164209c1660e0594b6271ae/nmatsuk}, description = {Data-Efficient Image Recognition with Contrastive Predictive Coding}, interhash = {371800272aca6e446695b33670629095}, intrahash = {f958ff01a164209c1660e0594b6271ae}, keywords = {backbone loss oneshot semisup unsup}, note = {cite arxiv:1905.09272}, timestamp = {2019-07-08T21:44:06.000+0200}, title = {Data-Efficient Image Recognition with Contrastive Predictive Coding}, url = {http://arxiv.org/abs/1905.09272}, year = 2019 }