Tiny ImageNet Visual Recognition Challenge

In this work, we investigate the effect of convolutional network depth, receptive field size, dropout layers, rectified activation unit type and dataset noise on its accuracy in Tiny-ImageNet Challenge settings. In order to make a thorough evaluation of the cause of the peformance improvement, we start with a basic 5 layer model with 5×5 convolutional receptive fields. We keep increasing network depth or reducing receptive field size, and continue applying modern techniques, such as PReLu and dropout, to the model. Our model achieves excellent performance even compared to state-of-the-art results, with 0.444 final error rate on the test set.