Publication

Detecting Road Obstacles by Erasing Them

Pascal Fua, Mathieu Salzmann, Krzysztof Maciej Lis, Sina Honari
2024
Journal Articles

Abstract

Vehicles can encounter a myriad of obstacles on the road, and it is impossible to record them all beforehand to train a detector. Instead, we select image patches and inpaint them with the surrounding road texture, which tends to remove obstacles from those patches. We then use a network trained to recognize discrepancies between the original patch and the inpainted one, which signals an erased obstacle.

Official source

https://infoscience.epfl.ch/entities/publication/cdab4aec-8a49-4ac1-a8ba-b2980c0516b2

About this result

This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.

Pascal Fua, Mathieu Salzmann, Krzysztof Maciej Lis, Sina Honari
2024
Journal Articles

Abstract

Official source

https://infoscience.epfl.ch/entities/publication/cdab4aec-8a49-4ac1-a8ba-b2980c0516b2

About this result

Related concepts (14)

Road

A road is a thoroughfare for the conveyance of traffic that mostly has an improved surface for use by vehicles (motorized and non-motorized) and pedestrians. Unlike streets, whose primary function is to serve as public spaces, the main function of roads is transportation. There are many types of roads, including parkways, avenues, controlled-access highways (freeways, motorways, and expressways), tollways, interstates, highways, thoroughfares, and local roads.

Recurrent neural network

A recurrent neural network (RNN) is one of the two broad types of artificial neural network, characterized by direction of the flow of information between its layers. In contrast to uni-directional feedforward neural network, it is a bi-directional artificial neural network, meaning that it allows the output from some nodes to affect subsequent input to the same nodes. Their ability to use internal state (memory) to process arbitrary sequences of inputs makes them applicable to tasks such as unsegmented, connected handwriting recognition or speech recognition.

Hopfield network

A Hopfield network (or Amari-Hopfield network, Ising model of a neural network or Ising–Lenz–Little model) is a form of recurrent artificial neural network and a type of spin glass system popularised by John Hopfield in 1982 as described by Shun'ichi Amari in 1972 and by Little in 1974 based on Ernst Ising's work with Wilhelm Lenz on the Ising model. Hopfield networks serve as content-addressable ("associative") memory systems with binary threshold nodes, or with continuous variables.

Related publications (32)

Task-driven neural network models predict neural dynamics of proprioception: Experimental data, activations and predictions of neural network models

Axel Bisi, Alberto Silvio Chiappa, Alexander Mathis, Alessandro Marin Vargas

Here we provide the neural data, activation and predictions for the best models and result dataframes of our article "Task-driven neural network models predict neural dynamics of proprioception". It contains the behavioral and neural experimental data (cu ...

EPFL Infoscience2024

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Volkan Cevher, Grigorios Chrysos, Fanghui Liu

Despite the widespread empirical success of ResNet, the generalization properties of deep ResNet are rarely explored beyond the lazy training regime. In this work, we investigate scaled ResNet in the limit of infinitely deep and wide neural networks, of wh ...

2024

Random matrix methods for high-dimensional machine learning models

Antoine Philippe Michel Bodin

In the rapidly evolving landscape of machine learning research, neural networks stand out with their ever-expanding number of parameters and reliance on increasingly large datasets. The financial cost and computational resources required for the training p ...

EPFL2024