End-to-end Learning Improves Static Object Geo-localization in Monocular Video

1 code implementation • 10 Apr 2020 • Mohamed Chaabane, Lionel Gueguen, Ameni Trabelsi, Ross Beveridge, Stephen O'Hara

We also show that the end-to-end system performance is further improved via joint-training of the constituent models.

Multi-Object Tracking Pose Estimation +1

Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations

1 code implementation • 18 Aug 2019 • Luming Liang, Sen Deng, Lionel Gueguen, Mingqiang Wei, Xinming Wu, Jing Qin

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise.

Salt-And-Pepper Noise Removal

Faster Neural Networks Straight from JPEG

1 code implementation • NeurIPS 2018 • Lionel Gueguen, Alex Sergeev, Ben Kadlec, Rosanne Liu, Jason Yosinski

In this paper we modify \libjpeg to produce DCT coefficients directly, modify a ResNet-50 network to accommodate the differently sized and strided input, and evaluate performance on ImageNet.

Joint Mapping and Calibration via Differentiable Sensor Fusion

no code implementations • 21 Nov 2018 • Jonathan P. Chen, Fritz Obermeyer, Vladimir Lyapunov, Lionel Gueguen, Noah D. Goodman

Our algorithm outperforms our current production baseline based on k-means clustering.

Clustering Probabilistic Programming +2

Large-Scale Damage Detection Using Satellite Imagery

no code implementations • CVPR 2015 • Lionel Gueguen, Raffay Hamid

Satellite imagery is a valuable source of information for assessing damages in distressed areas undergoing a calamity, such as an earthquake or an armed conflict.