Yahoo's recently open sourced neural network, open_nsfw, is a fine tuned Residual Network which scores images on a scale of to on its suitability for use in the workplace. [...]
What makes an image NSFW, according to Yahoo? I explore this question with a clever new visualization technique by Nguyen et al.. Like Google's Deep Dream, this visualization trick works by maximally activating certain neurons of the classifier. Unlike deep dream, we optimize these activations by performing descent on a parameterization of the manifold of natural images. This parametrization takes the form of a Generative Network, G, trained adversarially on an unrelated dataset of natural images. [...]
Not surprisingly, the results of the optimization are clearly pornographic.
Synthesizing Pareidolia [...] This explains the phenomena above, as the SFW neuron gets excited on the sight of rolling hills and running brooks, and the excitations of NSFW correlate with, well, pornography. The classifier takes in both these expert opinions, and combines them democratically [...] Since most pornography does not take place with a Thomas Kinkade painting in the background, this is a fair heuristic for most real world problems. But what happens if we try to excite both neurons simultaneously?