no code implementations • 8 May 2024 • Gabriele Berton, Gabriele Goletto, Gabriele Trivigno, Alex Stoken, Barbara Caputo, Carlo Masone
Precise, pixel-wise geolocalization of astronaut photography is critical to unlocking the potential of this unique type of remotely sensed Earth data, particularly for its use in disaster management and climate change research.
no code implementations • 16 Apr 2024 • Gabriele Trivigno, Carlo Masone, Barbara Caputo, Torsten Sattler
This involves training an implicit scene representation or learning features while optimizing a camera pose-based loss.
1 code implementation • 28 Mar 2024 • Gabriele Berton, Gabriele Trivigno, Barbara Caputo, Carlo Masone
As a mitigation to this problem, we propose a novel Joint Image and Sequence Training protocol (JIST) that leverages large uncurated sets of images through a multi-task learning framework.
1 code implementation • 11 Mar 2024 • Gabriele Berton, Alex Stoken, Barbara Caputo, Carlo Masone
Astronaut photography, spanning six decades of human spaceflight, presents a unique Earth observations dataset with immense value for both scientific research and disaster response.
no code implementations • 20 Feb 2024 • Claudia Cuttano, Antonio Tavera, Fabio Cermelli, Giuseppe Averta, Barbara Caputo
Many practical applications require training of semantic segmentation models on unlabelled datasets and their execution on low-resource hardware.
no code implementations • 6 Oct 2023 • Niccolò Cavagnero, Luca Robbiano, Francesca Pistilli, Barbara Caputo, Giuseppe Averta
Neural Networks design is a complex and often daunting task, particularly for resource-constrained scenarios typical of mobile-sized models.
no code implementations • 2 Oct 2023 • Debora Caldarola, Barbara Caputo, Marco Ciccone
To address these issues and improve the robustness and generalization capabilities of the global model, we propose WIMA (Window-based Model Averaging).
1 code implementation • 23 Sep 2023 • Eros Fanì, Marco Ciccone, Barbara Caputo
We propose FedDrive v2, an extension of the Federated Learning benchmark for Semantic Segmentation in Autonomous Driving.
no code implementations • 8 Sep 2023 • Shyam Nandan Rai, Fabio Cermelli, Barbara Caputo, Carlo Masone
Segmenting unknown or anomalous object instances is a critical task in autonomous driving applications, and it is approached traditionally as a per-pixel classification problem.
3 code implementations • ICCV 2023 • Gabriele Berton, Gabriele Trivigno, Barbara Caputo, Carlo Masone
Visual Place Recognition is a task that aims to predict the place of an image (called query) based solely on its visual features.
Ranked #2 on Visual Place Recognition on SF-XL test v2
1 code implementation • ICCV 2023 • Shyam Nandan Rai, Fabio Cermelli, Dario Fontanel, Carlo Masone, Barbara Caputo
We propose a paradigm change by shifting from a per-pixel classification to a mask classification.
Ranked #1 on Scene Segmentation on StreetHazards (using extra training data)
no code implementations • 24 Jul 2023 • Amirshayan Nasirimajd, Simone Alberto Peirone, Chiara Plizzari, Barbara Caputo
As only unlabelled target data are available under the UDA setting, we use a standard pseudo-labeling strategy for extracting action labels for the target.
1 code implementation • 17 Jul 2023 • Gabriele Trivigno, Gabriele Berton, Juan Aragon, Barbara Caputo, Carlo Masone
Our method, Divide&Classify (D&C), enjoys the fast inference of classification solutions and an accuracy competitive with retrieval methods on the fine-grained, city-wide setting.
no code implementations • ICCV 2023 • Chiara Plizzari, Toby Perrett, Barbara Caputo, Dima Damen
We propose and address a new generalisation problem: can a model trained for action recognition successfully classify actions when they are performed within a previously unseen scenario and in a previously unseen location?
1 code implementation • 12 Apr 2023 • Giovanni Barbarani, Mohamad Mostafa, Hajali Bayramov, Gabriele Trivigno, Gabriele Berton, Carlo Masone, Barbara Caputo
Despite recent advances, recognizing the same place when the query comes from a significantly different distribution is still a major hurdle for state of the art retrieval methods.
1 code implementation • ICCV 2023 • Gabriele Trivigno, Gabriele Berton, Juan Aragon, Barbara Caputo, Carlo Masone
In this paper we investigate whether we can effectively approach this task as a classification problem, thus bypassing the need for a similarity search.
1 code implementation • 6 Nov 2022 • Gabriele Goletto, Mirco Planamente, Barbara Caputo, Giuseppe Averta
To enable a safe and effective human-robot cooperation, it is crucial to develop models for the identification of human activities.
no code implementations • 12 Oct 2022 • Edoardo Arnaudo, Antonio Tavera, Fabrizio Dominici, Carlo Masone, Barbara Caputo
We investigate the task of unsupervised domain adaptation in aerial semantic segmentation and discover that the current state-of-the-art algorithms designed for autonomous driving based on domain mixing do not translate well to the aerial setting.
1 code implementation • 5 Oct 2022 • Donald Shenaj, Eros Fanì, Marco Toldo, Debora Caldarola, Antonio Tavera, Umberto Michieli, Marco Ciccone, Pietro Zanuttigh, Barbara Caputo
Federated Learning (FL) has recently emerged as a possible way to tackle the domain shift in real-world Semantic Segmentation (SS) without compromising the private nature of the collected data.
no code implementations • 9 Sep 2022 • Mirco Planamente, Gabriele Goletto, Gabriele Trivigno, Giuseppe Averta, Barbara Caputo
In this report, we describe the technical details of our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition.
no code implementations • 24 Aug 2022 • Dario Fontanel, Matteo Tarantino, Fabio Cermelli, Barbara Caputo
Object detection methods have witnessed impressive improvements in the last years thanks to the design of novel neural network architectures and the availability of large scale datasets.
1 code implementation • 8 Jul 2022 • Riccardo Mereu, Gabriele Trivigno, Gabriele Berton, Carlo Masone, Barbara Caputo
In robotics, Visual Place Recognition is a continuous process that receives as input a video stream to produce a hypothesis of the robot's current position within a map of known places.
1 code implementation • 17 Jun 2022 • Niccolò Cavagnero, Luca Robbiano, Barbara Caputo, Giuseppe Averta
In the last decade, most research in Machine Learning contributed to the improvement of existing models, with the aim of increasing the performance of neural networks for the solution of a variety of different tasks.
1 code implementation • 19 Apr 2022 • Fabio Cermelli, Antonino Geraci, Dario Fontanel, Barbara Caputo
We propose to handle these missing annotations by revisiting the standard knowledge distillation framework.
1 code implementation • 17 Apr 2022 • Antonio Tavera, Edoardo Arnaudo, Carlo Masone, Barbara Caputo
We observe that the existing methods used for this task are designed without considering two characteristics of the aerial data: (i) the top-down perspective implies that the model cannot rely on a fixed semantic structure of the scene, because the same scene may be experienced with different rotations of the sensor; (ii) there can be a strong imbalance in the distribution of semantic classes because the relevant objects of the scene may appear at extremely different scales (e. g., a field of crops and a small vehicle).
1 code implementation • CVPR 2022 • Gabriele Berton, Riccardo Mereu, Gabriele Trivigno, Carlo Masone, Gabriela Csurka, Torsten Sattler, Barbara Caputo
In this paper, we propose a new open-source benchmarking framework for Visual Geo-localization (VG) that allows to build, train, and test a wide range of commonly used architectures, with the flexibility to change individual components of a geo-localization pipeline.
2 code implementations • CVPR 2022 • Gabriele Berton, Carlo Masone, Barbara Caputo
Visual Geo-localization (VG) is the task of estimating the position where a given photo was taken by comparing it with a large database of images of known locations.
Ranked #2 on Visual Place Recognition on MSLS
1 code implementation • 22 Mar 2022 • Debora Caldarola, Barbara Caputo, Marco Ciccone
Models trained in federated settings often suffer from degraded performances and fail at generalizing, especially when facing heterogeneous scenarios.
1 code implementation • 28 Feb 2022 • Lidia Fantauzzo, Eros Fanì, Debora Caldarola, Antonio Tavera, Fabio Cermelli, Marco Ciccone, Barbara Caputo
For similar reasons, Federated Learning has been recently introduced as a new machine learning paradigm aiming to learn a global model while preserving privacy and leveraging data on millions of remote devices.
1 code implementation • 31 Jan 2022 • Fabio Cermelli, Massimiliano Mancini, Samuel Rota Buló, Elisa Ricci, Barbara Caputo
To tackle these issues, we introduce a novel incremental class learning approach for semantic segmentation taking into account a peculiar aspect of this task: since each training step provides annotation only for a subset of all possible classes, pixels of the background class exhibit a semantic shift.
1 code implementation • 26 Jan 2022 • Riccardo Zaccone, Andrea Rizzardi, Debora Caldarola, Marco Ciccone, Barbara Caputo
data severely impairs both the performance of the trained neural network and its convergence rate, increasing the number of communication rounds requested to reach a performance comparable to that of the centralized scenario.
1 code implementation • 24 Jan 2022 • Valerio Paolicelli, Antonio Tavera, Carlo Masone, Gabriele Berton, Barbara Caputo
In this paper we address the task of visual place recognition (VPR), where the goal is to retrieve the correct GPS coordinates of a given query image against a huge geotagged gallery.
1 code implementation • CVPR 2022 • Chiara Plizzari, Mirco Planamente, Gabriele Goletto, Marco Cannici, Emanuele Gusso, Matteo Matteucci, Barbara Caputo
However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications.
1 code implementation • 7 Dec 2021 • Edoardo Arnaudo, Fabio Cermelli, Antonio Tavera, Claudio Rossi, Barbara Caputo
Incremental learning represents a crucial task in aerial image processing, especially given the limited availability of large-scale annotated datasets.
1 code implementation • 7 Dec 2021 • Chiara Plizzari, Mirco Planamente, Gabriele Goletto, Marco Cannici, Emanuele Gusso, Matteo Matteucci, Barbara Caputo
However, the ever-growing field of event-based vision has, to date, overlooked the potential of event cameras in such applications.
1 code implementation • CVPR 2022 • Fabio Cermelli, Dario Fontanel, Antonio Tavera, Marco Ciccone, Barbara Caputo
As opposed to existing approaches, that need to generate pseudo-labels offline, we use an auxiliary classifier, trained with image-level labels and regularized by the segmentation model, to obtain pseudo-supervision online and update the model incrementally.
1 code implementation • 22 Oct 2021 • Antonio Tavera, Carlo Masone, Barbara Caputo
To the best of our knowledge, we are the first to present a real-time adversarial approach for assessing the domain adaption problem in semantic segmentation.
1 code implementation • 22 Oct 2021 • Antonio Tavera, Fabio Cermelli, Carlo Masone, Barbara Caputo
The pixel-wise adversarial training is assisted by a novel sample selection procedure, that handles the imbalance between source and target data, and a knowledge distillation strategy, that avoids overfitting towards the few target images.
no code implementations • 19 Oct 2021 • Mirco Planamente, Chiara Plizzari, Emanuele Alberti, Barbara Caputo
First person action recognition is becoming an increasingly researched area thanks to the rising popularity of wearable cameras.
1 code implementation • ICCV 2021 • Gabriele Berton, Carlo Masone, Valerio Paolicelli, Barbara Caputo
Dense local features matching is robust against changes in illumination and occlusions, but not against viewpoint shifts which are a fundamental aspect of geolocalization.
1 code implementation • 9 Jul 2021 • Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Barbara Caputo
Robotic visual systems operating in the wild must act in unconstrained scenarios, under different environmental conditions while facing a variety of semantic concepts, including unknown ones.
1 code implementation • 5 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.
no code implementations • 1 Jul 2021 • Chiara Plizzari, Mirco Planamente, Emanuele Alberti, Barbara Caputo
In this report, we describe the technical details of our submission to the EPIC-Kitchens-100 Unsupervised Domain Adaptation (UDA) Challenge in Action Recognition.
no code implementations • 4 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.
no code implementations • 3 Jun 2021 • Mirco Planamente, Chiara Plizzari, Emanuele Alberti, Barbara Caputo
First person action recognition is an increasingly researched topic because of the growing popularity of wearable cameras.
1 code implementation • 1 Jun 2021 • Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Barbara Caputo
Current state of the art of anomaly segmentation uses generative models, exploiting their incapability to reconstruct patterns unseen during training.
no code implementations • 29 Apr 2021 • Debora Caldarola, Massimiliano Mancini, Fabio Galasso, Marco Ciccone, Emanuele Rodolà, Barbara Caputo
Clustering may reduce heterogeneity by identifying the domains, but it deprives each cluster model of the data and supervision of others.
1 code implementation • 21 Apr 2021 • Giuseppe Pastore, Fabio Cermelli, Yongqin Xian, Massimiliano Mancini, Zeynep Akata, Barbara Caputo
Being able to segment unseen classes not observed during training is an important technical challenge in deep learning, because of its potential to reduce the expensive annotation required for semantic segmentation.
no code implementations • 25 Mar 2021 • Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
Most deep UDA approaches operate in a single-source, single-target scenario, i. e. they assume that the source and the target samples arise from a single distribution.
no code implementations • 25 Mar 2021 • Massimiliano Mancini, Elisa Ricci, Barbara Caputo, Samuel Rota Buló
In this work, we provide a general formulation of binary mask based models for multi-domain learning by affine transformations of the original network parameters.
no code implementations • 23 Mar 2021 • Mirco Planamente, Chiara Plizzari, Marco Cannici, Marco Ciccone, Francesco Strada, Andrea Bottino, Matteo Matteucci, Barbara Caputo
Event cameras are novel bio-inspired sensors, which asynchronously capture pixel-level intensity changes in the form of "events".
1 code implementation • 12 Feb 2021 • Luca Robbiano, Muhammad Rameez Ur Rahman, Fabio Galasso, Barbara Caputo, Fabio Maria Carlucci
Unsupervised Domain Adaptation (UDA) is a key issue in visual recognition, as it allows to bridge different visual domains enabling robust performances in the real world.
1 code implementation • 15 Dec 2020 • Matteo A. Senese, Alberto Benincasa, Barbara Caputo, Giuseppe Rizzo
Our approach makes use of a neural architecture based on transformer with a multi-attentive structure that conditions the response of the agent on the request made by the user and on the product the user is referring to.
1 code implementation • 30 Nov 2020 • Fabio Cermelli, Massimiliano Mancini, Yongqin Xian, Zeynep Akata, Barbara Caputo
Semantic segmentation models have two fundamental weaknesses: i) they require large training sets with costly pixel-level annotations, and ii) they have a static output space, constrained to the classes of the training set.
2 code implementations • 14 Oct 2020 • Gabriele Moreno Berton, Valerio Paolicelli, Carlo Masone, Barbara Caputo
We address the task of cross-domain visual place recognition, where the goal is to geolocalize a given query image against a labeled gallery, in the case where the query and the gallery belong to different visual domains.
no code implementations • 4 Aug 2020 • Levi O. Vasconcelos, Massimiliano Mancini, Davide Boscaini, Samuel Rota Bulo, Barbara Caputo, Elisa Ricci
Recent unsupervised domain adaptation methods based on deep architectures have shown remarkable performance not only in traditional classification tasks but also in more complex problems involving structured predictions (e. g. semantic segmentation, depth estimation).
no code implementations • 24 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.
Ranked #79 on Domain Generalization on PACS
1 code implementation • ECCV 2020 • Massimiliano Mancini, Zeynep Akata, Elisa Ricci, Barbara Caputo
The key idea of CuMix is to simulate the test-time domain and semantic shift using images and features from unseen domains and categories generated by mixing up the multiple source domains and categories available during training.
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.
3 code implementations • 21 Apr 2020 • Mohammad Reza Loghmani, Luca Robbiano, Mirco Planamente, Kiru Park, Barbara Caputo, Markus Vincze
Unsupervised Domain Adaptation (DA) exploits the supervision of a label-rich source dataset to make predictions on an unlabeled target dataset by aligning the two data distributions.
no code implementations • 20 Apr 2020 • Dario Fontanel, Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo
While convolutional neural networks have brought significant advances in robot vision, their ability is often limited to closed world scenarios, where the number of semantic concepts to be recognized is determined by the available training set.
no code implementations • 17 Apr 2020 • Emanuele Alberti, Antonio Tavera, Carlo Masone, Barbara Caputo
To support work in this direction, this paper contributes a new large scale, synthetic dataset for semantic segmentation with more than 100 different source visual domains.
no code implementations • 10 Feb 2020 • Mirco Planamente, Andrea Bottino, Barbara Caputo
Wearable cameras are becoming more and more popular in several applications, increasing the interest of the research community in developing approaches for recognizing actions from the first-person point of view.
1 code implementation • CVPR 2020 • Fabio Cermelli, Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo
Current strategies fail on this task because they do not consider a peculiar aspect of semantic segmentation: since each training step provides annotation only for a subset of all possible classes, pixels of the background class (i. e. pixels that do not belong to any other classes) exhibit a semantic distribution shift.
Ranked #3 on Domain 11-5 on Cityscapes
no code implementations • 9 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.
no code implementations • 4 Jun 2019 • Massimiliano Mancini, Hakan Karaoguz, Elisa Ricci, Patric Jensfelt, Barbara Caputo
While today's robots are able to perform sophisticated tasks, they can only act on objects they have been trained to recognize.
1 code implementation • 1 Apr 2019 • Fabio Cermelli, Massimiliano Mancini, Elisa Ricci, Barbara Caputo
Deep networks have brought significant advances in robot perception, enabling to improve the capabilities of robots in several visual tasks, ranging from object detection and recognition to pose estimation, semantic scene segmentation and many others.
1 code implementation • CVPR 2019 • Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
The ability to categorize is a cornerstone of visual intelligence, and a key functionality for artificial, autonomous visual machines.
2 code implementations • 16 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.
Ranked #3 on Domain Generalization on NICO Animal
no code implementations • 28 Sep 2018 • Antonio D'Innocente, Barbara Caputo
Visual recognition systems are meant to work in the real world.
Ranked #82 on Domain Generalization on PACS
1 code implementation • 3 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.
no code implementations • 31 Jul 2018 • Silvia Bucci, Mohammad Reza Loghmani, Barbara Caputo
Evaluations have been done using different data types: RGB only, depth only and RGB-D over the following datasets, designed for the robotic community: RGB-D Object Dataset (ROD), Web Object Dataset (WOD), Autonomous Robot Indoor Dataset (ARID), Big Berkeley Instance Recognition Dataset (BigBIRD) and Active Vision Dataset.
no code implementations • 31 Jul 2018 • Mirco Planamente, Mohammad Reza Loghmani, Barbara Caputo
Technological development aims to produce generations of increasingly efficient robots able to perform complex tasks.
no code implementations • 3 Jul 2018 • Massimiliano Mancini, Hakan Karaoguz, Elisa Ricci, Patric Jensfelt, Barbara Caputo
This novel dataset allows for testing the robustness of robot visual recognition algorithms to a series of different domain shifts both in isolation and unified.
no code implementations • 15 Jun 2018 • Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
A long standing problem in visual object categorization is the ability of algorithms to generalize across different testing conditions.
Ranked #112 on Domain Generalization on PACS
1 code implementation • 5 Jun 2018 • Mohammad Reza Loghmani, Mirco Planamente, Barbara Caputo, Markus Vincze
Providing machines with the ability to recognize objects like humans has always been one of the primary goals of machine vision.
1 code implementation • 30 May 2018 • Massimiliano Mancini, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
Our method develops from the intuition that, given a set of different classification models associated to known domains (e. g. corresponding to multiple environments, robots), the best model for a new sample in the novel domain can be computed directly at test time by optimally combining the known models.
no code implementations • 28 May 2018 • Massimiliano Mancini, Elisa Ricci, Barbara Caputo, Samuel Rota Bulò
Visual recognition algorithms are required today to exhibit adaptive abilities.
2 code implementations • CVPR 2018 • Massimiliano Mancini, Lorenzo Porzi, Samuel Rota Bulò, Barbara Caputo, Elisa Ricci
Our approach is based on the introduction of two main components, which can be embedded into any existing CNN architecture: (i) a side branch that automatically computes the assignment of a source sample to a latent domain and (ii) novel layers that exploit domain membership information to appropriately align the distribution of the CNN internal feature representations to a reference distribution.
1 code implementation • 24 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.
no code implementations • 18 Sep 2017 • Mohammad Reza Loghmani, Barbara Caputo, Markus Vincze
The ability to recognize objects is an essential skill for a robotic system acting in human-populated environments.
no code implementations • 29 Aug 2017 • Andrea Gigli, Arjan Gijsberts, Valentina Gregori, Matteo Cognolato, Manfredo Atzori, Barbara Caputo
In this paper, we develop an automated way to detect stable fixations and show that gaze information is indeed helpful in predicting hand movements.
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.
Ranked #13 on Domain Adaptation on SVHN-to-MNIST
no code implementations • 5 May 2017 • Antonio D'Innocente, Fabio Maria Carlucci, Mirco Colosi, Barbara Caputo
Despite the impressive progress brought by deep network in visual object recognition, robot vision is still far from being a solved problem.
2 code implementations • ICCV 2017 • Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò
Here we take a different route, proposing to align the learned representations by embedding in any given network specific Domain Alignment Layers, designed to match the source and target feature distributions to a reference one.
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.
no code implementations • 27 Feb 2017 • Valentina Gregori, Arjan Gijsberts, Barbara Caputo
A number of studies have proposed to use domain adaptation to reduce the training efforts needed to control an upper-limb prosthesis exploiting pre-trained models from prior subjects.
no code implementations • 25 Feb 2017 • Massimiliano Mancini, Samuel Rota Bulò, Elisa Ricci, Barbara Caputo
This paper presents an approach for semantic place categorization using data obtained from RGB cameras.
no code implementations • 21 Feb 2017 • Fabio Maria Carlucci, Lorenzo Porzi, Barbara Caputo, Elisa Ricci, Samuel Rota Bulò
The empirical fact that classifiers, trained on given data collections, perform poorly when tested on data acquired in different settings is theoretically explained in domain adaptation through a shift among distributions of the source and target domains.
no code implementations • 11 Jan 2017 • Igor Barros Barbosa, Marco Cristani, Barbara Caputo, Aleksander Rognhaugen, Theoharis Theoharis
Re-identification is generally carried out by encoding the appearance of a subject in terms of outfit, suggesting scenarios where people do not change their attire.
no code implementations • 30 Sep 2016 • Fabio Maria Carlucci, Paolo Russo, Barbara Caputo
We show that the filters learned from such data collection, using the very same architecture typically used on visual data, learns very different filters, resulting in depth features (a) able to better characterize the different facets of depth images, and (b) complementary with respect to those derived from CNNs pre-trained on 2D datasets.
no code implementations • 26 Aug 2016 • Valentina Gregori, Barbara Caputo
So-called domain adaptation algorithms formalize this strategy and have indeed been shown to significantly reduce the amount of required training data for intact subjects for myoelectric movements classification.
no code implementations • 20 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.
no code implementations • CVPR 2016 • Ilja Kuzborskij, Fabio Maria Carlucci, Barbara Caputo
Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbor (NBNN)-based classifiers have lost momentum in the community.
no code implementations • 11 Apr 2016 • Rocco De Rosa, Ilaria Gori, Fabio Cuzzolin, Barbara Caputo, Nicolò Cesa-Bianchi
Recognising human activities from streaming videos poses unique challenges to learning algorithms: predictive models need to be scalable, incrementally trainable, and must remain bounded in size even when the data stream is arbitrarily long.
no code implementations • 8 Apr 2016 • Rocco De Rosa, Thomas Mensink, Barbara Caputo
Recent attempts, like the open world recognition framework, tried to inject dynamics into the system by detecting new unknown classes and adding them incrementally, while at the same time continuously updating the models for the known classes.
no code implementations • 12 Nov 2015 • Ilja Kuzborskij, Fabio Maria Carlucci, Barbara Caputo
Since Convolutional Neural Networks (CNNs) have become the leading learning paradigm in visual recognition, Naive Bayes Nearest Neighbour (NBNN)-based classifiers have lost momentum in the community.
no code implementations • 6 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.
no code implementations • 26 Mar 2015 • Faraz Saeedan, Barbara Caputo
Here we follow this approach, and show how a very simple, learning free Naive Bayes Nearest Neighbor (NBNN)-based domain adaptation algorithm can significantly alleviate the distribution mismatch among source and target data, especially when the number of classes and the number of sources grow.
no code implementations • 6 Aug 2014 • Ilja Kuzborskij, Francesco Orabona, Barbara Caputo
In this paper we consider the binary transfer learning problem, focusing on how to select and combine sources from a large pool to yield a good performance on a target task.
no code implementations • CVPR 2014 • Novi Patricia, Barbara Caputo
The transfer learning and domain adaptation problems originate from a distribution mismatch between the source and target data distribution.
no code implementations • 24 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.
no code implementations • CVPR 2013 • Ilja Kuzborskij, Francesco Orabona, Barbara Caputo
Since the seminal work of Thrun [17], the learning to learn paradigm has been defined as the ability of an agent to improve its performance at each task with experience, with the number of tasks.
no code implementations • NeurIPS 2009 • Jie Luo, Barbara Caputo, Vittorio Ferrari
Given a corpus of news items consisting of images accompanied by text captions, we want to find out ``whos doing what, i. e. associate names and action verbs in the captions to the face and body pose of the persons in the images.