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
Posted Content
Inverting and Visualizing Features for Object Detection
TL;DR: Four algorithms to visualize feature spaces commonly used in object detection are described, with different trade-offs in speed accuracy, and scalability, and their most successful algorithm uses ideas from sparse coding to learn a pair of dictionaries that enable regression between HOG features and natural images, and can invert features at interactive rates.
Journal ArticleDOI
Guest Editorial: Scene Understanding
TL;DR: In this issue, several papers offer improvements to image segmentation and labeling through use of region classifiers, detectors, and object and scene context.
Proceedings ArticleDOI
On combining information-theoretic and cryptographic approaches to network coding security against the pollution attack
TL;DR: This paper considers the pollution attack in network coded systems where network nodes are computationally limited and proposes a fountain-like network error correction code construction suitable for this purpose.
Posted Content
Visualizing Object Detection Features
TL;DR: Algorithms to visualize feature spaces used by object detectors are introduced to allow for a more intuitive understanding of recognition systems and suggest that creating a better learning algorithm or building bigger datasets is unlikely to correct these errors without improving the features.
Journal ArticleDOI
Mapping human visual representations in space and time by neural networks
TL;DR: CNNs are a promising formal model of human visual object recognition Combined with fMRI and MEG, they provide an integrated spatiotemporal and algorithmically explicit view of the first few hundred milliseconds of object recognition.