N2N Learning: Network to Network Compression via Policy Gradient Reinforcement Learning

no code implementations • ICLR 2018 • Anubhav Ashok, Nicholas Rhinehart, Fares Beainy, Kris M. Kitani

Our approach takes a larger `teacher' network as input and outputs a compressed `student' network derived from the `teacher' network.

Model Compression reinforcement-learning +2

Rotational Rectification Network: Enabling Pedestrian Detection for Mobile Vision

no code implementations • 19 Jun 2017 • Xinshuo Weng, Shangxuan Wu, Fares Beainy, Kris Kitani

To address this issue, we propose a Rotational Rectification Network (R2N) that can be inserted into any CNN-based pedestrian (or object) detector to adapt it to significant changes in camera rotation.

Pedestrian Detection valid

Visual Compiler: Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator

no code implementations • 15 Dec 2016 • Namhoon Lee, Xinshuo Weng, Vishnu Naresh Boddeti, Yu Zhang, Fares Beainy, Kris Kitani, Takeo Kanade

We introduce the concept of a Visual Compiler that generates a scene specific pedestrian detector and pose estimator without any pedestrian observations.

Human Detection Pose Estimation