Detecting Road Obstacles by Erasing Them

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.

Detecting Road Obstacles by Erasing Them

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

Deep Learning Generalization with Limited and Noisy Labels

Artificial Intelligence for road quality assessment in smart cities: a machine learning approach to acoustic data analysis

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

Deep Learning Generalization with Limited and Noisy Labels

Artificial Intelligence for road quality assessment in smart cities: a machine learning approach to acoustic data analysis