Trade-Off between Object Selectivity and Tolerance in Monkey Inferotemporal Cortex

By Davide Zoccolan, Minjoon Kouh, Tomaso A. Poggio, James J. DiCarlo. 2007

172 citations recorded by the source corpus.

Object recognition requires both selectivity among different objects and tolerance to vastly different retinal images of the same object, resulting from natural variation in (e.g.) position, size, illumination, and clutter. Thus, discovering neuronal responses that have object selectivity and tolerance to identity-preserving transformations is fundamental to understanding object recognition. Although selectivity and tolerance are found at the highest level of the primate ventral visual stream [the inferotemporal cortex (IT)], both properties are highly varied and poorly understood. If an IT neuron has very sharp selectivity for a unique combination of object features (“diagnostic features”), this might automatically endow it with high tolerance. However, this relationship cannot be taken as given; although some IT neurons are highly object selective and some are highly tolerant, the empirical connection of these key properties is unknown. In this study, we systematically measured both object selectivity and tolerance to different identity-preserving image transformations in the spiking responses of a population of monkey IT neurons. We found that IT neurons with high object selectivity typically have low tolerance (and vice versa), regardless of how object selectivity was quantified and the type of tolerance examined. The discovery of this trade-off illuminates object selectivity and tolerance in IT and unifies a range of previous, seemingly disparate results. This finding also argues against the idea that diagnostic conjunctions of features guarantee tolerance. Instead, it is naturally explained by object recognition models in which object selectivity is built through AND-like tuning mechanisms.

Subfields: Cognitive Neuroscience

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Cognitive Neuroscience

Citations in the corpus

Normalization as a canonical neural computation (2011, background): “Other examples of normalization in visual areas beyond V1 lie in the ventral pathway, where visual neurons are thought to perform a series of transformations that lead to object recognitio”
How does the brain solve visual object recognition? (2012, neutral): “Such invariance not only is a hallmark of primate vision, but also is found in evolutionarily less advanced species (e.g., rodents; Tafazoli et al., 2012; Zoccolan et al., 2009).”
Metamers of the ventral stream (2011, methodology): “Theories of object recognition posit that the growth of receptive field sizes in consecutive areas, as well as with eccentricity, confers invariance to geometric transformations, and cascaded models based on filtering, simple nonlinearities and successively broader spatial pooling have been used to ”
Using goal-driven deep learning models to understand sensory cortex (2016, background): “HMAX networks had some success reproducing high-level empirical observations, such as the tolerance ranges of inferior temporal (IT) cortex neurons 12,27 and the tradeoff between single-unit selectivity and tolerance 28 .”
Selectivity and tolerance (“invariance”) both increase as visual information propagates from cortical area V4 to IT (2010, methodology): “First, although highly selective IT neurons do exist, most neurons in IT are broadly tuned for different objects when tested with large sets of images (Desimone et al., 1984; Rolls and Tovee, 1995; Kreiman et al., 2006; Zoccolan et al., 2007).”
Adaptive Resonance Theory: How a brain learns to consciously attend, learn, and recognize a changing world (2013, background): “Many other paradoxical data may also be explained by these concepts, including how spatial attention can increase the perceived brightness of a surface (Carrasco, Penpeci-Talgar, & Eckstein, 2000; Reynolds & Desimone, 2003), how predictive remapping of eye position occurs (Duhamel, Colby, & Goldberg”