K
Kilian Q. Weinberger
Researcher at Cornell University
Publications - 241
Citations - 71535
Kilian Q. Weinberger is an academic researcher from Cornell University. The author has contributed to research in topics: Computer science & Deep learning. The author has an hindex of 76, co-authored 222 publications receiving 49707 citations. Previous affiliations of Kilian Q. Weinberger include University of Washington & Washington University in St. Louis.
Papers
More filters
Posted Content
Distance Metric Learning for Kernel Machines
TL;DR: SVML, a novel algorithm that seamlessly combines the learning of a Mahalanobis metric with the training of the RBF-SVM parameters, outperforms all alternative state-of-the-art metric learning algorithms in terms of accuracy and establishes itself as a serious alternative to the standard Euclidean metric with model selection by cross validation.
Proceedings Article
Low Frequency Adversarial Perturbation
TL;DR: In this paper, the authors restrict the search for adversarial images to a low frequency domain and demonstrate the efficacy of this technique by fooling the Google Cloud Vision platform with an unprecedented low number of model queries.
Patent
Context Aware Image Representation
TL;DR: In this paper, the authors identify metadata associated with each of the plurality of multimedia contents, and a grouping of the multimedia content into a plurality of groups is performed based on the contextual information.
Posted Content
Deep Manifold Traversal: Changing Labels with Convolutional Features
Jacob R. Gardner,Paul Upchurch,Matt J. Kusner,Yixuan Li,Kilian Q. Weinberger,Kavita Bala,John E. Hopcroft +6 more
TL;DR: Deep manifold traversal as mentioned in this paper approximates the manifold of natural images and morphs a test image along a traversal path away from a source class and towards a target class while staying near the manifold throughout.
Proceedings ArticleDOI
Train in Germany, Test in the USA: Making 3D Object Detectors Generalize
Yan Wang,Xiangyu Chen,Yurong You,Li Erran Li,Bharath Hariharan,Mark Campbell,Kilian Q. Weinberger,Wei-Lun Chao +7 more
TL;DR: In this paper, the authors consider the task of adapting 3D object detectors from one dataset to another, and they provide extensive experiments to investigate the true adaptation challenges and arrive at a surprising conclusion: the primary adaptation hurdle to overcome are differences in car sizes across geographic areas.