Search Results for author: Andrei Bursuc

Found 26 papers, 11 papers with code

Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data

1 code implementation30 Mar 2022 Corentin Sautier, Gilles Puy, Spyros Gidaris, Alexandre Boulch, Andrei Bursuc, Renaud Marlet

In this context, we propose a self-supervised pre-training method for 3D perception models that is tailored to autonomous driving data.

3D Object Detection 3D Semantic Segmentation +2

UnShadowNet: Illumination Critic Guided Contrastive Learning For Shadow Removal

no code implementations29 Mar 2022 Subhrajyoti Dasgupta, Arindam Das, Sudip Das, Andrei Bursuc, Ujjwal Bhattacharya, Senthil Yogamani

Shadows are frequently encountered natural phenomena that significantly hinder the performance of computer vision perception systems in practical settings, e. g., autonomous driving.

Autonomous Driving Contrastive Learning +1

What to Hide from Your Students: Attention-Guided Masked Image Modeling

no code implementations23 Mar 2022 Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, Yannis Avrithis, Andrei Bursuc, Konstantinos Karantzalos, Nikos Komodakis

Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM).

Language Modelling Masked Language Modeling +1

Drive&Segment: Unsupervised Semantic Segmentation of Urban Scenes via Cross-modal Distillation

1 code implementation21 Mar 2022 Antonin Vobecky, David Hurych, Oriane Siméoni, Spyros Gidaris, Andrei Bursuc, Patrick Pérez, Josef Sivic

This work investigates learning pixel-wise semantic image segmentation in urban scenes without any manual annotation, just from the raw non-curated data collected by cars which, equipped with cameras and LiDAR sensors, drive around a city.

Unsupervised Semantic Segmentation

Learning-based Preference Prediction for Constrained Multi-Criteria Path-Planning

no code implementations2 Aug 2021 Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin

The uncertain criterion represents the feasibility of driving through the path without requiring human intervention.

Robust Semantic Segmentation with Superpixel-Mix

1 code implementation2 Aug 2021 Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, Volker Blanz, Angela Yao

Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation.

Data Augmentation Semi-Supervised Semantic Segmentation +1

Constrained Shortest Path Search with Graph Convolutional Neural Networks

no code implementations2 Aug 2021 Kevin Osanlou, Christophe Guettier, Andrei Bursuc, Tristan Cazenave, Eric Jacopin

In this paper, we focus on shortest path search with mandatory nodes on a given connected graph.

Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search

no code implementations2 Aug 2021 Kevin Osanlou, Andrei Bursuc, Christophe Guettier, Tristan Cazenave, Eric Jacopin

More specifically, a graph neural network is used to assist the branch and bound algorithm in handling constraints associated with a desired solution path.

StyleLess layer: Improving robustness for real-world driving

no code implementations25 Mar 2021 Julien Rebut, Andrei Bursuc, Patrick Pérez

Robustness to various image corruptions, caused by changing weather conditions or sensor degradation and aging, is crucial for safety when such vehicles are deployed in the real world.

Autonomous Driving Semantic Segmentation

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

2 code implementations CVPR 2021 Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Pérez

With this in mind, we propose a teacher-student scheme to learn representations by training a convolutional net to reconstruct a bag-of-visual-words (BoW) representation of an image, given as input a perturbed version of that same image.

Object Detection Representation Learning +4

Encoding the latent posterior of Bayesian Neural Networks for uncertainty quantification

1 code implementation4 Dec 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

Bayesian neural networks (BNNs) have been long considered an ideal, yet unscalable solution for improving the robustness and the predictive uncertainty of deep neural networks.

Bayesian Inference Decision Making Under Uncertainty +4

One Versus all for deep Neural Network Incertitude (OVNNI) quantification

no code implementations1 Jun 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

This is due to the fact that modern DNNs are usually uncalibrated and we cannot characterize their epistemic uncertainty.

PLOP: Probabilistic poLynomial Objects trajectory Planning for autonomous driving

no code implementations9 Mar 2020 Thibault Buhet, Emilie Wirbel, Andrei Bursuc, Xavier Perrotton

Our model processes ego vehicle front-facing camera images and bird-eye view grid, computed from Lidar point clouds, with detections of past and present objects, in order to generate multiple trajectories for both ego vehicle and its neighbors.

Autonomous Driving Imitation Learning +2

Learning Representations by Predicting Bags of Visual Words

1 code implementation CVPR 2020 Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts, here called visual words.

Representation Learning

TRADI: Tracking deep neural network weight distributions for uncertainty estimation

no code implementations ECCV 2020 Gianni Franchi, Andrei Bursuc, Emanuel Aldea, Severine Dubuisson, Isabelle Bloch

During training, the weights of a Deep Neural Network (DNN) are optimized from a random initialization towards a nearly optimum value minimizing a loss function.

General Classification Out-of-Distribution Detection +1

This dataset does not exist: training models from generated images

no code implementations7 Nov 2019 Victor Besnier, Himalaya Jain, Andrei Bursuc, Matthieu Cord, Patrick Pérez

This naturally brings the question: Can we train a classifier only on the generated data?

Boosting Few-Shot Visual Learning with Self-Supervision

1 code implementation ICCV 2019 Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Pérez, Matthieu Cord

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data.

Few-Shot Learning Self-Supervised Learning

Understanding and Improving Kernel Local Descriptors

3 code implementations27 Nov 2018 Arun Mukundan, Giorgos Tolias, Andrei Bursuc, Hervé Jégou, Ondřej Chum

We propose a multiple-kernel local-patch descriptor based on efficient match kernels from pixel gradients.

Cannot find the paper you are looking for? You can Submit a new open access paper.