Tracking objects that change in appearance with phase synchrony

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Muzellec, Sabine, Linsley, Drew, Ashok, Alekh K., Mingolla, Ennio, Malik, Girik, VanRullen, Rufin, Serre, Thomas
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912254268538880
author Muzellec, Sabine
Linsley, Drew
Ashok, Alekh K.
Mingolla, Ennio
Malik, Girik
VanRullen, Rufin
Serre, Thomas
author_facet Muzellec, Sabine
Linsley, Drew
Ashok, Alekh K.
Mingolla, Ennio
Malik, Girik
VanRullen, Rufin
Serre, Thomas
contents Objects we encounter often change appearance as we interact with them. Changes in illumination (shadows), object pose, or the movement of non-rigid objects can drastically alter available image features. How do biological visual systems track objects as they change? One plausible mechanism involves attentional mechanisms for reasoning about the locations of objects independently of their appearances -- a capability that prominent neuroscience theories have associated with computing through neural synchrony. Here, we describe a novel deep learning circuit that can learn to precisely control attention to features separately from their location in the world through neural synchrony: the complex-valued recurrent neural network (CV-RNN). Next, we compare object tracking in humans, the CV-RNN, and other deep neural networks (DNNs), using FeatureTracker: a large-scale challenge that asks observers to track objects as their locations and appearances change in precisely controlled ways. While humans effortlessly solved FeatureTracker, state-of-the-art DNNs did not. In contrast, our CV-RNN behaved similarly to humans on the challenge, providing a computational proof-of-concept for the role of phase synchronization as a neural substrate for tracking appearance-morphing objects as they move about.
format Preprint
id arxiv_https___arxiv_org_abs_2410_02094
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Tracking objects that change in appearance with phase synchrony
Muzellec, Sabine
Linsley, Drew
Ashok, Alekh K.
Mingolla, Ennio
Malik, Girik
VanRullen, Rufin
Serre, Thomas
Artificial Intelligence
Computer Vision and Pattern Recognition
Neurons and Cognition
Objects we encounter often change appearance as we interact with them. Changes in illumination (shadows), object pose, or the movement of non-rigid objects can drastically alter available image features. How do biological visual systems track objects as they change? One plausible mechanism involves attentional mechanisms for reasoning about the locations of objects independently of their appearances -- a capability that prominent neuroscience theories have associated with computing through neural synchrony. Here, we describe a novel deep learning circuit that can learn to precisely control attention to features separately from their location in the world through neural synchrony: the complex-valued recurrent neural network (CV-RNN). Next, we compare object tracking in humans, the CV-RNN, and other deep neural networks (DNNs), using FeatureTracker: a large-scale challenge that asks observers to track objects as their locations and appearances change in precisely controlled ways. While humans effortlessly solved FeatureTracker, state-of-the-art DNNs did not. In contrast, our CV-RNN behaved similarly to humans on the challenge, providing a computational proof-of-concept for the role of phase synchronization as a neural substrate for tracking appearance-morphing objects as they move about.
title Tracking objects that change in appearance with phase synchrony
topic Artificial Intelligence
Computer Vision and Pattern Recognition
Neurons and Cognition
url https://arxiv.org/abs/2410.02094