Unsupervised Pre-Training of Image Features on Non-Curated Data

Pre-training general-purpose visual features with convolutional neural networks without relying on annotations is a challenging and important task. Most recent efforts in unsupervised feature learning have focused on either small or highly curated datasets like ImageNet, whereas using uncurated raw datasets was found to decrease the feature quality when evaluated on a transfer task. Our goal is to bridge the performance gap between unsupervised methods trained on curated data, which are costly to obtain, and massive raw datasets that are easily available. To that effect, we propose a new unsupervised approach which leverages self-supervision and clustering to capture complementary statistics from large-scale data. We validate our approach on 96 million images from YFCC100M, achieving state-of-the-art results among unsupervised methods on standard benchmarks, which confirms the potential of unsupervised learning when only uncurated data are available. We also show that pre-training a supervised VGG-16 with our method achieves 74.9% top-1 classification accuracy on the validation set of ImageNet, which is an improvement of +0.8% over the same network trained from scratch. Our code is available at https://github.com/facebookresearch/DeeperCluster.

1. Introduction

Pre-trained convolutional neural networks, or convnets, are important components of image recognition applications [7, 8, 38, 46]. They improve the generalization of models trained on a limited amount of data [39] and speed up the training on applications when annotated data is abundant [20]. Convnets produce good generic representations when they are pre-trained on large supervised datasets like ImageNet [11]. However, designing such fully-annotated datasets has required a significant effort from the research community in terms of data cleansing and manual labeling. Scaling up the annotation process to datasets that are orders of magnitude bigger raises important difficulties. Using raw metadata as an alternative has been shown to perform comparatively well [23, 41], even surpassing ImageNet pre-training when trained on billions of images [30]. However, metadata are not always available, and when they are, they do not necessarily cover the full extent of a dataset. These difficulties motivate the design of methods that learn transferable features without using any annotation.