13 citations · 23 across the 13 of their papers we have counts for
14 papers
Ensembling Pruned Attention Heads For Uncertainty-Aware Efficient Transformers
Firas Gabetni, Giuseppe Curci, Andrea Pilzer +3
Uncertainty quantification (UQ) is essential for deploying deep neural networks in safety-critical settings. Although methods like Deep Ensembles achieve strong UQ performance, the…
Towards Understanding and Quantifying Uncertainty for Text-to-Image Generation
Gianni Franchi, Dat Nguyen Trong, Nacim Belkhir +2
Uncertainty quantification in text-to-image (T2I) generative models is crucial for understanding model behavior and improving output reliability. In this paper, we are the first to…
Make Me a BNN: A Simple Strategy for Estimating Bayesian Uncertainty from Pre-trained Models
Gianni Franchi, Olivier Laurent, Maxence Leguéry +3
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real…
The Robust Semantic Segmentation UNCV2023 Challenge Results
Xuanlong Yu, Yi Zuo, Zitao Wang +34
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segment…
Fixing Overconfidence in Dynamic Neural Networks
Lassi Meronen, Martin Trapp, Andrea Pilzer +2
Dynamic neural networks are a recent technique that promises a remedy for the increasing size of modern deep learning models by dynamically adapting their computational cost to the…
Expansion of Visual Hints for Improved Generalization in Stereo Matching
Andrea Pilzer, Yuxin Hou, Niki Loppi +2
We introduce visual hints expansion for guiding stereo matching to improve generalization. Our work is motivated by the robustness of Visual Inertial Odometry (VIO) in computer vis…
Uncertainty-guided Source-free Domain Adaptation
Subhankar Roy, Martin Trapp, Andrea Pilzer +4
Source-free domain adaptation (SFDA) aims to adapt a classifier to an unlabelled target data set by only using a pre-trained source model. However, the absence of the source data a…
A Look at Improving Robustness in Visual-inertial SLAM by Moment Matching
Arno Solin, Rui Li, Andrea Pilzer
The fusion of camera sensor and inertial data is a leading method for ego-motion tracking in autonomous and smart devices. State estimation techniques that rely on non-linear filte…
Progressive Fusion for Unsupervised Binocular Depth Estimation using Cycled Networks
Andrea Pilzer, Stéphane Lathuilière, Dan Xu +3
Recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance. However, they require costly ground truth annotations during…
Structured Coupled Generative Adversarial Networks for Unsupervised Monocular Depth Estimation
Mihai Marian Puscas, Dan Xu, Andrea Pilzer +1
Inspired by the success of adversarial learning, we propose a new end-to-end unsupervised deep learning framework for monocular depth estimation consisting of two Generative Advers…
Refine and Distill: Exploiting Cycle-Inconsistency and Knowledge Distillation for Unsupervised Monocular Depth Estimation
Andrea Pilzer, Stéphane Lathuilière, Nicu Sebe +1
Nowadays, the majority of state of the art monocular depth estimation techniques are based on supervised deep learning models. However, collecting RGB images with associated depth…
Online Adaptation through Meta-Learning for Stereo Depth Estimation
Zhenyu Zhang, Stéphane Lathuilière, Andrea Pilzer +3
In this work, we tackle the problem of online adaptation for stereo depth estimation, that consists in continuously adapting a deep network to a target video recordedin an environm…
Unsupervised Adversarial Depth Estimation using Cycled Generative Networks
Andrea Pilzer, Dan Xu, Mihai Marian Puscas +2
While recent deep monocular depth estimation approaches based on supervised regression have achieved remarkable performance, costly ground truth annotations are required during tra…
Viraliency: Pooling Local Virality
Xavier Alameda-Pineda, Andrea Pilzer, Dan Xu +2
In our overly-connected world, the automatic recognition of virality - the quality of an image or video to be rapidly and widely spread in social networks - is of crucial importanc…