Search Results - "Deza, Arturo"

General object-based features account for letter perception by Janini, Daniel, Hamblin, Chris, Deza, Arturo, Konkle, Talia

“…After years of experience, humans become experts at perceiving letters. Is this visual capacity attained by learning specialized letter features, or by reusing…”
Get full text

Foveation induces Robustness to Scene Occlusion in Deep Neural Networks by Deza, Arturo, Konkle, Talia

Get full text

Understanding image virality by Deza, Arturo, Parikh, Devi

“…Virality of online content on social networking websites is an important but esoteric phenomenon often studied in fields like marketing, psychology and data…”
Get full text

How big should this object be? Perceptual influences on viewing-size preferences by Chen, Yi-Chia, Deza, Arturo, Konkle, Talia

“…When viewing objects depicted in a frame, observers prefer to view large objects like cars in larger sizes and smaller objects like cups in smaller sizes. That…”
Get full text

Peripheral Representations Enhance Dense Clutter Metrics in Free Search by Deza, Arturo, Eckstein, Miguel

Get full text

Quantifying Adversarial Sensitivity of a Model as a Function of the Image Distribution by Kunhardt, Owen, Deza, Arturo, Poggio, Tomaso

Get full text

How big should this object be? Perceptual influences on viewing-size preferences by Chen, Yi-Chia, Deza, Arturo, Konkle, Talia

Get full text

Hierarchically Local Tasks and Deep Convolutional Networks by Deza, Arturo, Banburski, Andrzej, Liao, Qianli, Poggio, Tomaso

Get full text

A foveated object detector that misses giant and misplaced targets in scenes by Jonnalagadda, Aditya, Deza, Arturo, Eckstein, Miguel

Get full text

The Influence of Visual Clutter on Search Guidance with Complex Scenes by Deza, Arturo, Taylor, Grant, Eckstein, Miguel

Get full text

Scene context reduces distractor set-size effects during search by Deza, Arturo, Akbas, Emre, Eckstein, Miguel

Get full text

Achieving Adversarial Robustness in Deep Learning-Based Overhead Imaging by Braun, Dagen, Reisman, Matthew, Dewell, Larry, Banburski-Fahey, Andrzej, Deza, Arturo, Poggio, Tomaso

“…The Intelligence, Surveillance, and Reconnaissance (ISR) community relies heavily on the use of overhead imagery for object detection and classification. In…”
Get full text

Assessment of Faster R-CNN in Man-Machine Collaborative Search by Deza, Arturo, Surana, Amit, Eckstein, Miguel P.

“…With the advent of modern expert systems driven by deep learning that supplement human experts (e.g. radiologists, dermatologists, surveillance scanners), we…”
Get full text

Joint rotational invariance and adversarial training of a dual-stream Transformer yields state of the art Brain-Score for Area V4 by Berrios, William, Deza, Arturo

“…Modern high-scoring models of vision in the brain score competition do not stem from Vision Transformers. However, in this paper, we provide evidence against…”
Get full text

Finding Biological Plausibility for Adversarially Robust Features via Metameric Tasks by Harrington, Anne, Deza, Arturo

“…Recent work suggests that representations learned by adversarially robust networks are more human perceptually-aligned than non-robust networks via image…”
Get full text

Emergent Properties of Foveated Perceptual Systems by Deza, Arturo, Konkle, Talia

“…The goal of this work is to characterize the representational impact that foveation operations have for machine vision systems, inspired by the foveated human…”
Get full text

The Effects of Image Distribution and Task on Adversarial Robustness by Kunhardt, Owen, Deza, Arturo, Poggio, Tomaso

“…In this paper, we propose an adaptation to the area under the curve (AUC) metric to measure the adversarial robustness of a model over a particular…”
Get full text

CUDA-Optimized real-time rendering of a Foveated Visual System by Malkin, Elian, Deza, Arturo, Poggio, Tomaso

“…The spatially-varying field of the human visual system has recently received a resurgence of interest with the development of virtual reality (VR) and neural…”
Get full text

On the use of Cortical Magnification and Saccades as Biological Proxies for Data Augmentation by Wang, Binxu, Mayo, David, Deza, Arturo, Barbu, Andrei, Conwell, Colin

“…Self-supervised learning is a powerful way to learn useful representations from natural data. It has also been suggested as one possible means of building…”
Get full text

Assessment of Faster R-CNN in Man-Machine collaborative search by Deza, Arturo, Surana, Amit, Eckstein, Miguel P

“…With the advent of modern expert systems driven by deep learning that supplement human experts (e.g. radiologists, dermatologists, surveillance scanners), we…”
Get full text