In this work we investigate the effect of the convolutional neural network depth on its accuracy in the large-scale image recognition task. Our main contribution is a thorough evaluation of networks of increasing depth using an architecture with very small (3x3) convolution filters, which shows that a significant improvement on the prior-art configurations can be achieved by pushing the depth to 16-19 weight layers. These findings were the basis of our ImageNet Challenge 2014 submission, where our team won the first and the second places in the localisation and classification tracks respectively.