Search Results for author: Manuel Lopez-Antequera

Found 2 papers, 0 papers with code

A Push-Pull Layer Improves Robustness of Convolutional Neural Networks

no code implementations29 Jan 2019 Nicola Strisciuglio, Manuel Lopez-Antequera, Nicolai Petkov

We propose a new layer in Convolutional Neural Networks (CNNs) to increase their robustness to several types of noise perturbations of the input images.

General Classification Image Classification

Training a Convolutional Neural Network for Appearance-Invariant Place Recognition

no code implementations27 May 2015 Ruben Gomez-Ojeda, Manuel Lopez-Antequera, Nicolai Petkov, Javier Gonzalez-Jimenez

In order for the network to learn the desired invariances, we train it with triplets of images selected from datasets which present a challenging variability in visual appearance.

Autonomous Driving

Cannot find the paper you are looking for? You can Submit a new open access paper.