A
Aditya Khosla
Researcher at Massachusetts Institute of Technology
Publications - 62
Citations - 71575
Aditya Khosla is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Object detection & Artificial neural network. The author has an hindex of 39, co-authored 61 publications receiving 50417 citations. Previous affiliations of Aditya Khosla include Stanford University & Open University of Catalonia.
Papers
More filters
Journal Article
Visualizing Object Detection Features
TL;DR: In this article, the authors introduce algorithms to visualize feature spaces used by object detectors by inverting a visual feature back to multiple natural images and finding that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector's failures.
Proceedings ArticleDOI
Image memorability and visual inception
TL;DR: The notion of image memorability and the elements that make it memorable are discussed and evidence for the phenomenon of visual inception is introduced: can the authors make people believe they have seen an image they have not?
Journal ArticleDOI
Visualizing Object Detection Features
TL;DR: In this article, the authors introduce algorithms to visualize feature spaces used by object detectors by inverting a visual feature back to multiple natural images and finding that these visualizations allow us to analyze object detection systems in new ways and gain new insight into the detector's failures.
Posted ContentDOI
Dynamics of scene representations in the human brain revealed by magnetoencephalography and deep neural networks
TL;DR: Together these data provide a first description of an electrophysiological signal for layout processing in humans, and a novel quantitative model of how spatial layout representations may emerge in the human brain.
Proceedings ArticleDOI
Towards Real-time Classification of Astronomical Transients
Ashish Mahabal,S. G. Djorgovski,Roy Williams,Andrew Drake,C. Donalek,Matthew J. Graham,B. Moghaddam,M. Turmon,J. Jewell,Aditya Khosla,Brandon S. Hensley +10 more
TL;DR: This work is investigating Bayesian methodologies for classification, as well as discriminated follow-up to optimize the use of available resources, including Naive Bayesian approach, and the non-parametric Gaussian process regression.