Object Recognition: Models

Poster Session: Wednesday, May 22, 2024, 8:30 am – 12:30 pm, Pavilion

Poster Title

First Author

From clear to noise: Investigating neural noise progression in visual system robustness

Jang, Hojin

3D shape recognition in humans and deep neural networks

Fu, Shuhao

Sparse components distinguish visual pathways and their alignment to neural networks

Marvi, Ammar

A biologically inspired framework for contrastive learning of visual representations: BioCLR

Han, Zhixian

Characteristics of the emergence of category selectivity in convolutional neural networks

Verosky, Niels J.

Spatial filters in neural network models of visual cortex do not need to be learned

Passi, Ananya

How to estimate noise ceilings for computational models of visual cortex

Chen, Zirui

Investigating power laws in neural network models of visual cortex

Townley, Keaton

Interpreting distributed population codes with feature-accentuated visual encoding models

Prince, Jacob S.

Evaluating the Alignment of Machine and Human Explanations in Visual Object Recognition through a Novel Behavioral Approach

Kashef Alghetaa, Yousif

Quantifying the Quality of Shape and Texture Representations in Deep Neural Network Models

Doshi, Fenil R.

Differential sensitivity of humans and deep networks to the amplitude and phase of shape features

Baker, Nicholas

Spatial Frequency Decoupling: Bio-inspired strategy for Network Robustness

Arslan, Suayb

Visual and auditory object recognition in relation to spatial abilities

Smithson, Conor J. R.

Geometric properties of object manifolds in neural network models of visual cortex

Bonner, Michael

When Machines Outshine Humans in Object Recognition, Benchmarking Dilemma

Darvishi Bayazi, Mohammad Javad