Semantic Scholar uses AI to extract papers important to this topic.
We present a simple self-training method that achieves 88.4% top-1 accuracy on ImageNet, which is 2.0% better than the state-of… Expand Convolutional Neural Networks (CNNs) are commonly thought to recognise objects by learning increasingly complex representations… Expand Deep learning thrives with large neural networks and large datasets. However, larger networks and larger datasets result in… Expand We propose two efficient approximations to standard convolutional neural networks: Binary-Weight-Networks and XNOR-Networks. In… Expand The ImageNet Large Scale Visual Recognition Challenge is a benchmark in object category classification and detection on hundreds… Expand Rectified activation units (rectifiers) are essential for state-of-the-art neural networks. In this work, we study rectifier… Expand We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC… Expand ImageNet is a large-scale hierarchical database of object classes. We propose to automatically populate it with pixelwise… Expand The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to… Expand The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to… Expand