Sort by: Year Popularity Relevance

Understanding Convolutional Neural Networks

 - 2016

Convoulutional Neural Networks (CNNs) exhibit extraordinary performance on a variety of machine learning tasks. However, their mathematical properties and behavior are quite poorly understood. There is some work, in the form of a framework, for analyzing the operations that they perform. The goal of this project is to present key results from thi...


Systematic evaluation of CNN advances on the ImageNet

, ,  - 2016

The paper systematically studies the impact of a range of recent advances in CNN architectures and learning methods on the object categorization (ILSVRC) problem. The evalution tests the influence of the following choices of the architecture: non-linearity (ReLU, ELU, maxout, compatibility with batch normalization), pooling variants (stochastic, ...


Optimal Testing of Self-Driving Cars

, ,  - 2017

Automotive manufacturers attempting to bring autonomous vehicles to market must make the case that their product is sufficiently safe for public deployment. Much of this case will likely rely upon outcomes from real-world testing, requiring manufacturers to be strategic about how they allocate testing resources in order to maximize their chances ...


MultiCol-SLAM - A Modular Real-Time Multi-Camera SLAM System

,  - 2016

The basis for most vision based applications like robotics, self-driving cars and potentially augmented and virtual reality is a robust, continuous estimation of the position and orientation of a camera system w.r.t the observed environment (scene). In recent years many vision based systems that perform simultaneous localization and mapping (SLAM...


A Minimal Closed-Form Solution for Multi-Perspective Pose Estimation using Points and Lines

, ,  - 2018

We propose a minimal solution for pose estimation using both points and lines for a multi-perspective camera. In this paper, we treat the multi-perspective camera as a collection of rigidly attached perspective cameras. These type of imaging devices are useful for several computer vision applications that require a large coverage such as surveill...


Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

, , , ,  - 2018

Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in th...


Evolving Boxes for Fast Vehicle Detection

, , , , ,  - 2017

We perform fast vehicle detection from traffic surveillance cameras. A novel deep learning framework, namely Evolving Boxes, is developed that proposes and refines the object boxes under different feature representations. Specifically, our framework is embedded with a light-weight proposal network to generate initial anchor boxes as well as to ea...


Criticality as It Could Be: organizational invariance as self-organized criticality in embodied agents

,  - 2017

This paper outlines a methodological approach for designing adaptive agents driving themselves near points of criticality. Using a synthetic approach we construct a conceptual model that, instead of specifying mechanistic requirements to generate criticality, exploits the maintenance of an organizational structure capable of reproducing critical ...


Total Recall: Understanding Traffic Signs using Deep Hierarchical Convolutional Neural Networks

, ,  - 2018

Recognizing Traffic Signs using intelligent systems can drastically reduce the number of accidents happening world-wide. With the arrival of Self-driving cars it has become a staple challenge to solve the automatic recognition of Traffic and Hand-held signs in the major streets. Various machine learning techniques like Random Forest, SVM as well ...


Exploring the Limitations of Behavior Cloning for Autonomous Driving

, , ,  - 2019

Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven cars. Behavior cloning in particular has been successfully used to learn simple visuomotor pol...