Search Results for author: Tatiana Tommasi

Found 40 papers, 16 papers with code

PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models

no code implementations18 Dec 2023 Antonio Alliegro, Yawar Siddiqui, Tatiana Tommasi, Matthias Nießner

In contrast to methods that use alternate 3D shape representations (e. g. implicit representations), our approach is a discrete denoising diffusion probabilistic model that operates natively on the polygonal mesh data structure.

Avg Denoising

MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers

no code implementations27 Nov 2023 Yawar Siddiqui, Antonio Alliegro, Alexey Artemov, Tatiana Tommasi, Daniele Sirigatti, Vladislav Rosov, Angela Dai, Matthias Nießner

We introduce MeshGPT, a new approach for generating triangle meshes that reflects the compactness typical of artist-created meshes, in contrast to dense triangle meshes extracted by iso-surfacing methods from neural fields.

Domain Randomization via Entropy Maximization

no code implementations3 Nov 2023 Gabriele Tiboni, Pascal Klink, Jan Peters, Tatiana Tommasi, Carlo D'Eramo, Georgia Chalvatzaki

Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL).

Reinforcement Learning (RL)

OpenPatch: a 3D patchwork for Out-Of-Distribution detection

no code implementations5 Oct 2023 Paolo Rabino, Antonio Alliegro, Francesco Cappio Borlino, Tatiana Tommasi

We advance the field by introducing OpenPatch that builds on a large pre-trained model and simply extracts from its intermediate features a set of patch representations that describe each known class.

Novelty Detection Out-of-Distribution Detection

Fairness meets Cross-Domain Learning: a new perspective on Models and Metrics

1 code implementation25 Mar 2023 Leonardo Iurada, Silvia Bucci, Timothy M. Hospedales, Tatiana Tommasi

Deep learning-based recognition systems are deployed at scale for several real-world applications that inevitably involve our social life.

Domain Adaptation Fairness

PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting

no code implementations13 Nov 2022 Gabriele Tiboni, Raffaello Camoriano, Tatiana Tommasi

Popular industrial robotic problems such as spray painting and welding require (i) conditioning on free-shape 3D objects and (ii) planning of multiple trajectories to solve the task.

3DOS: Towards 3D Open Set Learning -- Benchmarking and Understanding Semantic Novelty Detection on Point Clouds

1 code implementation23 Jul 2022 Antonio Alliegro, Francesco Cappio Borlino, Tatiana Tommasi

In recent years there has been significant progress in the field of 3D learning on classification, detection and segmentation problems.

Benchmarking Novelty Detection +1

Semantic Novelty Detection via Relational Reasoning

1 code implementation18 Jul 2022 Francesco Cappio Borlino, Silvia Bucci, Tatiana Tommasi

We claim that a tailored representation learning strategy may be the right solution for effective and efficient semantic novelty detection.

Autonomous Driving Edge-computing +5

Online vs. Offline Adaptive Domain Randomization Benchmark

1 code implementation29 Jun 2022 Gabriele Tiboni, Karol Arndt, Giuseppe Averta, Ville Kyrki, Tatiana Tommasi

However, transferring the acquired knowledge to the real world can be challenging due to the reality gap.

Fault-Aware Design and Training to Enhance DNNs Reliability with Zero-Overhead

no code implementations28 May 2022 Niccolò Cavagnero, Fernando Dos Santos, Marco Ciccone, Giuseppe Averta, Tatiana Tommasi, Paolo Rech

Deep Neural Networks (DNNs) enable a wide series of technological advancements, ranging from clinical imaging, to predictive industrial maintenance and autonomous driving.

Autonomous Driving

Contrastive Learning for Cross-Domain Open World Recognition

1 code implementation17 Mar 2022 Francesco Cappio Borlino, Silvia Bucci, Tatiana Tommasi

The ability to evolve is fundamental for any valuable autonomous agent whose knowledge cannot remain limited to that injected by the manufacturer.

Contrastive Learning

Distance-based Hyperspherical Classification for Multi-source Open-Set Domain Adaptation

1 code implementation5 Jul 2021 Silvia Bucci, Francesco Cappio Borlino, Barbara Caputo, Tatiana Tommasi

Vision systems trained in closed-world scenarios fail when presented with new environmental conditions, new data distributions, and novel classes at deployment time.

Contrastive Learning Style Transfer +1

Towards Fairness Certification in Artificial Intelligence

no code implementations4 Jun 2021 Tatiana Tommasi, Silvia Bucci, Barbara Caputo, Pietro Asinari

Thanks to the great progress of machine learning in the last years, several Artificial Intelligence (AI) techniques have been increasingly moving from the controlled research laboratory settings to our everyday life.

BIG-bench Machine Learning Decision Making +1

Multi-Modal RGB-D Scene Recognition Across Domains

1 code implementation26 Mar 2021 Andrea Ferreri, Silvia Bucci, Tatiana Tommasi

Indeed, learning to go from RGB to depth and vice-versa is an unsupervised procedure that can be trained jointly on data of multiple cameras and may help to bridge the gap among the extracted feature distributions.

Scene Classification Scene Recognition

Rethinking Domain Generalization Baselines

no code implementations22 Jan 2021 Francesco Cappio Borlino, Antonio D'Innocente, Tatiana Tommasi

Despite being very powerful in standard learning settings, deep learning models can be extremely brittle when deployed in scenarios different from those on which they were trained.

Data Augmentation Domain Generalization +1

Self-Supervised Learning Across Domains

no code implementations24 Jul 2020 Silvia Bucci, Antonio D'Innocente, Yujun Liao, Fabio Maria Carlucci, Barbara Caputo, Tatiana Tommasi

Human adaptability relies crucially on learning and merging knowledge from both supervised and unsupervised tasks: the parents point out few important concepts, but then the children fill in the gaps on their own.

Domain Generalization Object Recognition +2

On the Effectiveness of Image Rotation for Open Set Domain Adaptation

1 code implementation ECCV 2020 Silvia Bucci, Mohammad Reza Loghmani, Tatiana Tommasi

Open Set Domain Adaptation (OSDA) bridges the domain gap between a labeled source domain and an unlabeled target domain, while also rejecting target classes that are not present in the source.

Domain Adaptation

One-Shot Unsupervised Cross-Domain Detection

no code implementations ECCV 2020 Antonio D'Innocente, Francesco Cappio Borlino, Silvia Bucci, Barbara Caputo, Tatiana Tommasi

Despite impressive progress in object detection over the last years, it is still an open challenge to reliably detect objects across visual domains.

object-detection Object Detection

Joint Supervised and Self-Supervised Learning for 3D Real-World Challenges

no code implementations15 Apr 2020 Antonio Alliegro, Davide Boscaini, Tatiana Tommasi

Point cloud processing and 3D shape understanding are very challenging tasks for which deep learning techniques have demonstrated great potentials.

3D Shape Classification General Classification +3

Learning to Generalize One Sample at a Time with Self-Supervision

no code implementations9 Oct 2019 Antonio D'Innocente, Silvia Bucci, Barbara Caputo, Tatiana Tommasi

Although deep networks have significantly increased the performance of visual recognition methods, it is still challenging to achieve the robustness across visual domains that is necessary for real-world applications.

Auxiliary Learning Domain Generalization +1

Tackling Partial Domain Adaptation with Self-Supervision

no code implementations12 Jun 2019 Silvia Bucci, Antonio D'Innocente, Tatiana Tommasi

Domain adaptation approaches have shown promising results in reducing the marginal distribution difference among visual domains.

Domain Generalization Partial Domain Adaptation

Domain Generalization by Solving Jigsaw Puzzles

2 code implementations16 Mar 2019 Fabio Maria Carlucci, Antonio D'Innocente, Silvia Bucci, Barbara Caputo, Tatiana Tommasi

Human adaptability relies crucially on the ability to learn and merge knowledge both from supervised and unsupervised learning: the parents point out few important concepts, but then the children fill in the gaps on their own.

Domain Generalization Image Classification +1

Hallucinating Agnostic Images to Generalize Across Domains

1 code implementation3 Aug 2018 Fabio M. Carlucci, Paolo Russo, Tatiana Tommasi, Barbara Caputo

The ability to generalize across visual domains is crucial for the robustness of artificial recognition systems.

Domain Generalization Unsupervised Domain Adaptation

Adaptive Deep Learning through Visual Domain Localization

1 code implementation24 Feb 2018 Gabriele Angeletti, Barbara Caputo, Tatiana Tommasi

We exploit this through the learning of maps that spatially ground the domain and quantify the degree of shift, embedded into an end-to-end deep domain adaptation architecture.

Domain Adaptation

From source to target and back: symmetric bi-directional adaptive GAN

no code implementations CVPR 2018 Paolo Russo, Fabio Maria Carlucci, Tatiana Tommasi, Barbara Caputo

The effectiveness of generative adversarial approaches in producing images according to a specific style or visual domain has recently opened new directions to solve the unsupervised domain adaptation problem.

Image Generation Unsupervised Domain Adaptation

Training Deep Networks without Learning Rates Through Coin Betting

6 code implementations NeurIPS 2017 Francesco Orabona, Tatiana Tommasi

Instead, we reduce the optimization process to a game of betting on a coin and propose a learning-rate-free optimal algorithm for this scenario.

Stochastic Optimization

Learning Deep Visual Object Models From Noisy Web Data: How to Make it Work

1 code implementation IEEE Xplore: 2017 Nizar Massouh, Francesca Babiloni, Tatiana Tommasi, Jay Young, Nick Hawes, Barbara Caputo

We contribute to this research thread with two findings: (1) a study correlating a given level of noisily labels to the expected drop in accuracy, for two deep architectures, on two different types of noise, that clearly identifies GoogLeNet as a suitable architecture for learning from Web data; (2) a recipe for the creation of Web datasets with minimal noise and maximum visual variability, based on a visual and natural language processing concept expansion strategy.

Object Object Categorization +1

Combining Multiple Cues for Visual Madlibs Question Answering

no code implementations1 Nov 2016 Tatiana Tommasi, Arun Mallya, Bryan Plummer, Svetlana Lazebnik, Alexander C. Berg, Tamara L. Berg

This paper presents an approach for answering fill-in-the-blank multiple choice questions from the Visual Madlibs dataset.

Attribute General Classification +3

Solving Visual Madlibs with Multiple Cues

no code implementations11 Aug 2016 Tatiana Tommasi, Arun Mallya, Bryan Plummer, Svetlana Lazebnik, Alexander C. Berg, Tamara L. Berg

This paper focuses on answering fill-in-the-blank style multiple choice questions from the Visual Madlibs dataset.

Activity Prediction Attribute +4

Learning the Roots of Visual Domain Shift

no code implementations20 Jul 2016 Tatiana Tommasi, Martina Lanzi, Paolo Russo, Barbara Caputo

In this paper we focus on the spatial nature of visual domain shift, attempting to learn where domain adaptation originates in each given image of the source and target set.

Domain Adaptation General Classification +1

Active Transfer Learning with Zero-Shot Priors: Reusing Past Datasets for Future Tasks

no code implementations ICCV 2015 Efstratios Gavves, Thomas Mensink, Tatiana Tommasi, Cees G. M. Snoek, Tinne Tuytelaars

How can we reuse existing knowledge, in the form of available datasets, when solving a new and apparently unrelated target task from a set of unlabeled data?

Active Learning General Classification +2

A Deeper Look at Dataset Bias

no code implementations6 May 2015 Tatiana Tommasi, Novi Patricia, Barbara Caputo, Tinne Tuytelaars

The presence of a bias in each image data collection has recently attracted a lot of attention in the computer vision community showing the limits in generalization of any learning method trained on a specific dataset.

Joint cross-domain classification and subspace learning for unsupervised adaptation

no code implementations17 Nov 2014 Basura Fernando, Tatiana Tommasi, Tinne Tuytelaars

Domain adaptation aims at adapting the knowledge acquired on a source domain to a new different but related target domain.

Domain Adaptation domain classification +1

Location Recognition Over Large Time Lags

no code implementations26 Sep 2014 Basura Fernando, Tatiana Tommasi, Tinne Tuytelaars

Would it be possible to automatically associate ancient pictures to modern ones and create fancy cultural heritage city maps?

Domain Adaptation

A Testbed for Cross-Dataset Analysis

no code implementations24 Feb 2014 Tatiana Tommasi, Tinne Tuytelaars, Barbara Caputo

Since its beginning visual recognition research has tried to capture the huge variability of the visual world in several image collections.

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