Extreme Translation Tolerance in Humans and Machines
Ryan P. Blything, Ivan Vankov, Casimir J. H. Ludwig, Jeffrey S. Bowers · 2019 Conference on Cognitive Computational Neuroscience · 2019
What mechanism supports our ability to recognize objects over a wide range of different retinal locations?Most research in psychology and neuroscience suggests that learning to identify a novel object at one retinal location only supports the ability to identify that object at nearby retinal locations, and to date, neural network models of object identification show a similar restriction in generalization.As a consequence, it is widely assumed that objects need to be learned at multiple locations.We challenge this view and show the capacity to generalize across retinal locations (what we call on-line translation tolerance) has been underestimated in humans and artificial neural networks.Two eye tracking studies demonstrate that novel objects can be recognized following translations of 9°and even 18°.Additionally, computational studies showed that convolutional neural networks can achieve similarly robust generalization when a mechanism (Global Average Pooling) was built in to generate larger receptive fields.