Saved in:
Bibliographic Details
Main Authors: Jang, Hojin, Sinha, Pawan, Boix, Xavier
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2407.19072
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910544740483072
author Jang, Hojin
Sinha, Pawan
Boix, Xavier
author_facet Jang, Hojin
Sinha, Pawan
Boix, Xavier
contents Configural processing, the perception of spatial relationships among an object's components, is crucial for object recognition. However, the teleology and underlying neurocomputational mechanisms of such processing are still elusive, notwithstanding decades of research. We hypothesized that processing objects via configural cues provides a more robust means to recognizing them relative to local featural cues. We evaluated this hypothesis by devising identification tasks with composite letter stimuli and comparing different neural network models trained with either only local or configural cues available. We found that configural cues yielded more robust performance to geometric transformations such as rotation or scaling. Furthermore, when both features were simultaneously available, configural cues were favored over local featural cues. Layerwise analysis revealed that the sensitivity to configural cues emerged later relative to local feature cues, possibly contributing to the robustness to pixel-level transformations. Notably, this configural processing occurred in a purely feedforward manner, without the need for recurrent computations. Our findings with letter stimuli were successfully extended to naturalistic face images. Thus, our study provides neurocomputational evidence that configural processing emerges in a naïve network based on task contingencies, and is beneficial for robust object processing under varying viewing conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2407_19072
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Configural processing as an optimized strategy for robust object recognition in neural networks
Jang, Hojin
Sinha, Pawan
Boix, Xavier
Computer Vision and Pattern Recognition
Artificial Intelligence
Configural processing, the perception of spatial relationships among an object's components, is crucial for object recognition. However, the teleology and underlying neurocomputational mechanisms of such processing are still elusive, notwithstanding decades of research. We hypothesized that processing objects via configural cues provides a more robust means to recognizing them relative to local featural cues. We evaluated this hypothesis by devising identification tasks with composite letter stimuli and comparing different neural network models trained with either only local or configural cues available. We found that configural cues yielded more robust performance to geometric transformations such as rotation or scaling. Furthermore, when both features were simultaneously available, configural cues were favored over local featural cues. Layerwise analysis revealed that the sensitivity to configural cues emerged later relative to local feature cues, possibly contributing to the robustness to pixel-level transformations. Notably, this configural processing occurred in a purely feedforward manner, without the need for recurrent computations. Our findings with letter stimuli were successfully extended to naturalistic face images. Thus, our study provides neurocomputational evidence that configural processing emerges in a naïve network based on task contingencies, and is beneficial for robust object processing under varying viewing conditions.
title Configural processing as an optimized strategy for robust object recognition in neural networks
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2407.19072