The paper proposes a new way of learning image representations from unlabeled data by predicting the image rotations. The problem formulation implicitly encourages the learned representation to be informative about the (foreground) object and its rotation. The idea is simple, but it turns out to be very effective. The authors demonstrate strong performance in multiple transfer learning scenarios, such as ImageNet classification, PASCAL classification, PASCAL segmentation, and CIFAR-10 classification.
Paper && code
The paper proposes a new way of learning image representations from unlabeled data by predicting the image rotations. The problem formulation implicitly encourages the learned representation to be informative about the (foreground) object and its rotation. The idea is simple, but it turns out to be very effective. The authors demonstrate strong performance in multiple transfer learning scenarios, such as ImageNet classification, PASCAL classification, PASCAL segmentation, and CIFAR-10 classification.