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
Proceedings Article
Learning a metric for music similarity
TL;DR: Five different principled ways to embed songs into a Euclidean metric space are described, each of the six approaches rotate and scale the raw feature space with a linear transform and tune the parameters of these models using a song-classification task with content-based features.
Journal ArticleDOI
Boosted multi-task learning
Olivier Chapelle,Pannagadatta K. Shivaswamy,Srinivas Vadrevu,Kilian Q. Weinberger,Ya Zhang,Belle L. Tseng +5 more
TL;DR: A novel algorithm for multi-task learning with boosted decision trees that enables implicit data sharing and regularization and is derived using the relationship between ℓ1-regularization and boosting.
Posted Content
Low Frequency Adversarial Perturbation
TL;DR: This paper proposes to restrict the search for adversarial images to a low frequency domain, which is readily compatible with many existing black-box attack frameworks and consistently reduces their query cost by 2 to 4 times.
Proceedings ArticleDOI
Anytime Stereo Image Depth Estimation on Mobile Devices
Yan Wang,Zihang Lai,Gao Huang,Brian H. Wang,Laurens van der Maaten,Mark Campbell,Kilian Q. Weinberger +6 more
TL;DR: In this article, the authors propose an end-to-end learned approach for disparity prediction in the anytime setting, during which the model can be queried at any time to output its current best estimate.
Proceedings ArticleDOI
End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection
Rui Qian,Divyansh Garg,Yan Wang,Yurong You,Serge Belongie,Bharath Hariharan,Mark Campbell,Kilian Q. Weinberger,Wei-Lun Chao +8 more
TL;DR: In this paper, a new framework based on differentiable Change of Representation (CoR) modules is introduced to allow the entire pseudo-LiDAR (PL) pipeline to be trained end-to-end.