Interpretation of ResNet by Visualization of Preferred Stimulus in Receptive Fields
This provides insights into the biological plausibility of ResNet for researchers in computer vision and neuroscience, though it is incremental as it builds on existing visualization methods.
The study tackled the interpretation of ResNet from a biological viewpoint by investigating its receptive fields on ImageNet classification, finding that it contains orientation selective neurons and double opponent color neurons, and suggesting that some inactive neurons in the first layer affect classification.
One of the methods used in image recognition is the Deep Convolutional Neural Network (DCNN). DCNN is a model in which the expressive power of features is greatly improved by deepening the hidden layer of CNN. The architecture of CNNs is determined based on a model of the visual cortex of mammals. There is a model called Residual Network (ResNet) that has a skip connection. ResNet is an advanced model in terms of the learning method, but it has not been interpreted from a biological viewpoint. In this research, we investigate the receptive fields of a ResNet on the classification task in ImageNet. We find that ResNet has orientation selective neurons and double opponent color neurons. In addition, we suggest that some inactive neurons in the first layer of ResNet affect the classification task.