No area of machine learning has advanced more rapidly that image classifiers in the past decade.  While higher level intelligence has been harder to come by in the world of AI, image recognition feels like a baked technology, with Convolutional Neural Nets dominating the field.  But a new data set from researchers at IBM and MIT called ObjectNet shows that today’s state of the art systems struggle badly when dealing with the messy real world. With objects at weird angles, or partially hidden, or covered  up, even the best accuracy scores plunge from 97% to 50-55%.