Research Area
Year Published

203 Results

May 2, 2016

Metric Learning with Adaptive Density Discrimination

ICLR

Distance metric learning approaches learn a transformation to a representation space in which distance is in correspondence with a predefined notion of similarity.

By: Oren Rippel, Manohar Paluri, Piotr Dollar, Lubomir Bourdev

December 15, 2015

Learning to Segment Object Candidates

NIPS

In this paper, we propose a new way to generate object proposals, introducing an approach based on a discriminative convolutional network. Our model obtains substantially higher object recall using fewer proposals. We also show that our model is able to generalize to unseen categories it has not seen during training.

By: Pedro Oliveira, Ronan Collobert, Piotr Dollar

February 17, 2015

What Makes for Effective Detection Proposals?

PAMI

An in depth study of object proposals and their effect on object detection performance.

By: Jan Hosang, Rodrigo Benenson, Piotr Dollar, Bernt Schiele