A Detailed Look at Scale and Translation Invariance in a Hierarchical Neural Model of Visual Object Recognition

The HMAX model has recently been proposed by Riesenhuber & Poggio [15] as a hierarchical model of positionand size-invariant object recognition in visual cortex. It has also turned out to model successfully a number of other properties of the ventral visual stream (the visual pathway thought to be crucial for object recognition in cortex), and particularly of (view-tuned) neurons in macaque inferotemporal cortex, the brain area at the top of the ventral stream. The original modeling study [15] only used “paperclip” stimuli, as in the corresponding physiology experiment [8], and did not explore systematically how model units’ invariance properties depended on model parameters. In this study, we aimed at a deeper understanding of the inner workings of HMAX and its performance for various parameter settings and “natural” stimulus classes. We examined HMAX responses for different stimulus sizes and positions systematically and found a dependence of model units’ responses on stimulus position for which a quantitative description is offered. Scale invariance properties were found to be dependent on the particular stimulus class used. Moreover, a given view-tuned unit can exhibit substantially different invariance ranges when mapped with different probe stimuli. This has potentially interesting ramifications for experimental studies in which the receptive field of a neuron and its scale invariance properties are usually only mapped with probe objects of a single type. Copyright c ©Massachusetts Institute of Technology, 2002 This report describes research done within the Center for Biological & Computational Learning in the Department of Brain & Cognitive Sciences and in the Artificial Intelligence Laboratory at the Massachusetts Institute of Technology. This research was sponsored by grants from: Office of Naval Research (DARPA) under contract No. N00014-00-1-0907, National Science Foundation (ITR) under contract No. IIS-0085836, National Science Foundation (KDI) under contract No. DMS9872936, and National Science Foundation under contract No. IIS-9800032. Additional support was provided by: AT&T, Central Research Institute of Electric Power Industry, Center for e-Business (MIT), Eastman Kodak Company, DaimlerChrysler AG, Compaq, Honda R&D Co., Ltd., ITRI, Komatsu Ltd., Merrill-Lynch, Mitsubishi Corporation, NEC Fund, Nippon Telegraph & Telephone, Oxygen, Siemens Corporate Research, Inc., Sumitomo Metal Industries, Toyota Motor Corporation, WatchVision Co., Ltd., and The Whitaker Foundation. R.S. is supported by grants from the German National Scholarship Foundation, the German Academic Exchange Service and the State of Bavaria. M.R. is supported by a McDonnell-Pew Award in Cognitive Neuroscience.