Country
TowardsImprovingCalibrationinObjectDetection UnderDomainShift
Unfortunately, very little to no attention is paid towards addressing calibration ofDNN-based visual object detectors, that occupysimilar space and importance inmanydecision making systems astheir visual classification counterparts. In this work, we study the calibration of DNN-based object detection models, particularly under domain shift.
Deep Network for the Integrated 3D Sensing of Multiple People in Natural Images
Andrei Zanfir, Elisabeta Marinoiu, Mihai Zanfir, Alin-Ionut Popa, Cristian Sminchisescu
Wepresent MubyNet -afeed-forward,multitask, bottom upsystem fortheintegrated localization, as well as 3d pose and shape estimation, of multiple people inmonocular images.
On the Power of SVD in Clustering Problems
In many applications, the number of features could be very large.
On the Power of SVD in the Stochastic Block Model
A popular heuristic method for improving clustering results is to apply dimensionality reduction before running clustering algorithms.
Learning Nearest Neighbor Graphs from Noisy Distance Samples
Blake Mason, Ardhendu Tripathy, Robert Nowak
Neural Information Processing Systems http://nips.cc/
Gaussian Process Conditional Density Estimation
Vincent Dutordoir, Hugh Salimbeni, James Hensman, Marc Deisenroth
Neural Information Processing Systems http://nips.cc/
fcc3dc27672a12510babe448d665e152-Paper-Conference.pdf
We show the universality of depth-2 group convolutional neural networks (GCNNs) inaunified and constructivemanner based ontheridgelet theory.