O
Olivier J. Hénaff
Researcher at Center for Neural Science
Publications - 21
Citations - 1621
Olivier J. Hénaff is an academic researcher from Center for Neural Science. The author has contributed to research in topics: Computer science & Population. The author has an hindex of 9, co-authored 18 publications receiving 1019 citations. Previous affiliations of Olivier J. Hénaff include New York University & Howard Hughes Medical Institute.
Papers
More filters
Posted Content
Data-Efficient Image Recognition with Contrastive Predictive Coding
Olivier J. Hénaff,Aravind Srinivas,Jeffrey De Fauw,Ali Razavi,Carl Doersch,S. M. Ali Eslami,Aaron van den Oord +6 more
TL;DR: This work revisit and improve Contrastive Predictive Coding, an unsupervised objective for learning such representations which make the variability in natural signals more predictable, and produces features which support state-of-the-art linear classification accuracy on the ImageNet dataset.
Posted Content
Are we done with ImageNet
TL;DR: A significantly more robust procedure for collecting human annotations of the ImageNet validation set is developed, which finds the original ImageNet labels to no longer be the best predictors of this independently-collected set, indicating that their usefulness in evaluating vision models may be nearing an end.
Proceedings Article
Data-Efficient Image Recognition with Contrastive Predictive Coding
Journal ArticleDOI
Perceptual straightening of natural videos.
TL;DR: A methodology for estimating the curvature of an internal trajectory from human perceptual judgments is developed, and this is used to test three distinct predictions: natural sequences that are highly curved in the space of pixel intensities should be substantially straighter perceptually; in contrast, artificial sequences that is straight in the intensity domain should be more curved perceptually.
Journal ArticleDOI
Representation of visual uncertainty through neural gain variability
TL;DR: A model of visual cortex is proposed in which average neural response strength encodes stimulus features, while cross-neuron variability in response gain encodes the uncertainty of these features, and neural gain variability tracks stimulus uncertainty across the visual hierarchy.