Same data, same features: modern ImageNet-trained convolutional neural networks learn the same thing
Deep convolutional neural networks (CNNs) are the dominant technology in computer vision today. Much of the recent computer vision literature can be thought of as a competition to find the best architecture for vision within the deep convolutional framework. Despite all the effort invested in developing sophisticated convolutional architectures, however, it's not clear how different from each other the best CNNs really are. This thesis measures the similarity between ten well-known CNNs, in terms of the properties they extract from images. I find that the properties extracted by each of the ten ...
(For more, see "View full record.")