Skip to footer

Lionel Gueguen

Lionel Gueguen
1 BLOG ARTICLES 4 RESEARCH PAPERS
Lionel Gueguen is a senior software engineer with Uber ATG.

Engineering Blog Articles

Faster Neural Networks Straight from JPEG

Uber AI Labs introduces a method for making neural networks that process images faster and more accurately by leveraging JPEG representations.

Research Papers

Rotated Rectangles for Symbolized Building Footprint Extraction

M. Dickenson, L. Gueguen
Building footprints (BFP) provide useful visual context for users of digital maps when navigating in space. This paper proposes a method for extracting and symbolizing building footprints from satellite imagery using a convolutional neural network (CNN). [...] [PDF at Computer Vision Foundation open access]
Conference on Computer Vision and Pattern Recognition (CVPR), 2018

Joint Mapping and Calibration via Differentiable Sensor Fusion

J. Chen, F. Obermeyer, V. Lyapunov, L. Gueguen, N. Goodman
We leverage automatic differentiation (AD) and probabilistic programming to develop an end-to-end optimization algorithm for batch triangulation of a large number of unknown objects. Given noisy detections extracted from noisily geo-located street level imagery without depth information, we jointly estimate the number and location of objects of different types, together with parameters for sensor noise characteristics and prior distribution of objects conditioned on side information. [...] [PDF at arXiv]
Computer Vision and Pattern Recognition (CVPR), 2018

Faster Neural Networks Straight from JPEG

L. Gueguen, A. Sergeev, B. Kadlec, R. Liu, J. Yosinski
The simple, elegant approach of training convolutional neural networks (CNNs) directly from RGB pixels has enjoyed overwhelming empirical success. But can more performance be squeezed out of networks by using different input representations? In this paper we propose and explore a simple idea: train CNNs directly on the blockwise discrete cosine transform (DCT) coefficients computed and available in the middle of the JPEG codec. [...] [PDF at NeurIPS Proceedings]
Advances in Neural Information Processing Systems (NeurIPS), 2018

Uber-Text: A Large-Scale Dataset for Optical Character Recognition from Street-Level Imagery

Y. Zhang, L. Gueguen, I. Zharkov, P. Zhang, K. Seifert, B. Kadlec Optical Character Recognition (OCR) approaches have been widely advanced in recent years thanks to the resurgence of deep learning. The state-of-the-art models are mainly trained on the datasets consisting of the constrained scenes. Detecting and recognizing text from the real-world images remains a technical challenge. [...] [PDF at MIT]
Conference on Computer Vision and Pattern Recognition (CVPR), 2017

Popular Articles