Search Results for author:
Found 18 papers, 5 papers with code
On the Metrics for Evaluating Monocular Depth Estimation
In particular, we take the task of 3D object detection on point clouds as a proxy of on-board perception.
Scaling Self-Supervised End-to-End Driving with Multi-View Attention Learning
With only self-supervised training data, our model yields almost expert performance in CARLA's Nocrash metrics and could be rival to the SOTA models requiring large amounts of human labeled data.
Unstructured Road Segmentation using Hypercolumn based Random Forests of Local experts
We propose a method to detect and segment roads with a random forest classifier of local experts with superpixel based machine-learned features.
Action-Based Representation Learning for Autonomous Driving
Human drivers produce a vast amount of data which could, in principle, be used to improve autonomous driving systems.
Co-training for On-board Deep Object Detection
Providing ground truth supervision to train visual models has been a bottleneck over the years, exacerbated by domain shifts which degenerate the performance of such models.
Distributed Learning and Inference with Compressed Images
Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift.
Slanted Stixels: A way to represent steep streets
This work presents and evaluates a novel compact scene representation based on Stixels that infers geometric and semantic information.
Temporal Coherence for Active Learning in Videos
Our active learning criterion is based on the estimated number of errors in terms of false positives and false negatives.
Self-supervised Domain Adaptation for Computer Vision Tasks
Additionally, we propose two complementary strategies to further boost the domain adaptation accuracy on semantic segmentation within our method, consisting of prediction layer alignment and batch normalization calibration.
Joint Coarse-And-Fine Reasoning for Deep Optical Flow
We propose a novel representation for dense pixel-wise estimation tasks using CNNs that boosts accuracy and reduces training time, by explicitly exploiting joint coarse-and-fine reasoning.
Metric Learning for Novelty and Anomaly Detection
When neural networks process images which do not resemble the distribution seen during training, so called out-of-distribution images, they often make wrong predictions, and do so too confidently.
Monocular Depth Estimation by Learning from Heterogeneous Datasets
Depth estimation provides essential information to perform autonomous driving and driver assistance.
Ranked #26 on
Monocular Depth Estimation
on KITTI Eigen split
Rotate your Networks: Better Weight Consolidation and Less Catastrophic Forgetting
In this paper we propose an approach to avoiding catastrophic forgetting in sequential task learning scenarios.
From Virtual to Real World Visual Perception using Domain Adaptation -- The DPM as Example
However, since the models learned with virtual data must operate in the real world, we still need to perform domain adaptation (DA).
Node-Adapt, Path-Adapt and Tree-Adapt:Model-Transfer Domain Adaptation for Random Forest
Random Forest (RF) is a successful paradigm for learning classifiers due to its ability to learn from large feature spaces and seamlessly integrate multi-class classification, as well as the achieved accuracy and processing efficiency.
The SYNTHIA Dataset: A Large Collection of Synthetic Images for Semantic Segmentation of Urban Scenes
In order to answer this question we have generated a synthetic collection of diverse urban images, named SYNTHIA, with automatically generated class annotations.
Road Detection by One-Class Color Classification: Dataset and Experiments
These algorithms reduce the effect of lighting variations and weather conditions by exploiting the discriminant/invariant properties of different color representations.
Hierarchical Adaptive Structural SVM for Domain Adaptation
In both cases, we show how HA-SSVM is effective in increasing the detection/recognition accuracy with respect to adaptation strategies that ignore the structure of the target data.
