← Search

Vasha DuTell

2 accepted papers

2024

COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery

ICLR 2024poster

Evaluating deep neural networks (DNNs) as models of human perception has given rich insights into both human visual processing and representational properties of DNNs. We extend this work by analyzing how well DNNs perform compared to humans when constrained by peripheral vision -- which limits huma…

Cited by 3SourcePDFScholar
2023

Exploring perceptual straightness in learned visual representations

ICLR 2023poster

Humans have been shown to use a ''straightened'' encoding to represent the natural visual world as it evolves in time (Henaff et al. 2019). In the context of discrete video sequences, ''straightened'' means that changes between frames follow a more linear path in representation space at progressivel…

Cited by 5SourcePDFScholar