Search Results for author:
Found 5 papers, 1 papers with code
Gaussian Latent Representations for Uncertainty Estimation using Mahalanobis Distance in Deep Classifiers
Recent works show that the data distribution in a network's latent space is useful for estimating classification uncertainty and detecting Out-of-distribution (OOD) samples.
How To Train Your HERON
In this paper we apply Deep Reinforcement Learning (Deep RL) and Domain Randomization to solve a navigation task in a natural environment relying solely on a 2D laser scanner.
A Study on Trees's Knots Prediction from their Bark Outer-Shape
In the industry, the value of wood-logs strongly depends on their internal structure and more specifically on the knots' distribution inside the trees.
Robust Monocular Edge Visual Odometry through Coarse-to-Fine Data Association
In this work, we propose a monocular visual odometry framework, which allows exploiting the best attributes of edge feature for illumination-robust camera tracking, while at the same time ameliorating the performance degradation of edge mapping.
Semantic Nearest Neighbor Fields Monocular Edge Visual-Odometry
The core of our approach is a semantic nearest neighbor field that facilitates a robust data association of edges across frames using semantics.
