Journal: IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Deep convolutional neural network architecture codenamed Inception that achieves new state-of-the-art for classification and detection in the ImageNet Large Scale Visual Recognition challenge 2014. The main aspect of this architecture is the improved utilization of the computing resources inside the network. While the depth and width of the network is increased, the costs are kept constant by a carefully crafted design. Architectural decisions are based on the Hebbian principle and the intuition of multi scale processing.