Datasets, features, learning, and models in visual recognition

Visual recognition is a fundamental research topic in computer vision. This dissertation explores datasets, features, learning, and models used for visual recognition. In order to train visual models and evaluate different recognition algorithms, this dissertation develops an approach to collect object image datasets on web pages using an analysis of text around the image and of image appearance. This method exploits established online knowledge resources (Wikipedia pages for text; Flickr and Caltech data sets for images). The resources provide rich text and object appearance information. This dissertation describes results on two datasets. The first is Berg’s collection of 10 animal categories; on this dataset, we significantly outperform previous approaches. On an additional set of 5 categories, experimental results show the effectiveness of the method. Images are represented as features for visual recognition. This dissertation introduces a text-based image feature and demonstrates that it consistently improves performance on hard object classification problems. The feature is built using an auxiliary dataset of images annotated with tags, downloaded from the Internet. Image tags are noisy. The method obtains the text features of an unannotated image from the tags of its k-nearest neighbors in this auxiliary collection. A visual classifier presented with an object viewed under novel circumstances (say, a new viewing direction) must rely on its visual examples. This text feature may not change, because the auxiliary dataset likely contains a similar picture. While the tags associated with images are noisy, they are more stable when appearance changes. The performance of this feature is tested using PASCAL VOC 2006 and 2007 datasets. This feature performs well; it consistently improves the performance of visual object classifiers, and is particularly effective when the training dataset is small. With more and more collected training data, computational cost becomes a bottleneck, especially when training sophisticated classifiers such as kernelized SVM. This dissertation proposes a fast training algorithm called Stochastic Intersection Kernel Machine (SIKMA). This proposed training method will be useful for many vision problems, as it can produce a kernel classifier that is more accurate than a linear classifier, and can be trained on tens of thousands of examples in two minutes. It processes training examples one by one in a sequence, so memory cost is no longer the bottleneck to process large scale datasets. This dissertation applies this approach to train classifiers of Flickr groups with many group training examples. The resulting Flickr group prediction scores can be used to measure image similarity between two images. Experimental results on the Corel dataset and a PASCAL VOC dataset show the learned Flickr features perform better on image matching, retrieval, and classification than conventional visual features. Visual models are usually trained to best separate positive and negative training examples. However, when recognizing a large number of object categories, there may not be enough training examples for most objects, due to the intrinsic long-tailed distribution of objects in the real world. This dissertation proposes an approach to use comparative object similarity. The key insight is that, given a set of object categories which are similar and a set of categories which are dissimilar, a good object model should respond more strongly to examples from similar categories than to examples from dissimilar categories. This dissertation develops a regularized kernel machine algorithm to use this category dependent similarity regularization. Experiments on hundreds of categories show that our method can make significant improvement for categories with few or even no positive examples.

Scene Mapping and Understanding by Robotic Vision

The first mechanical Automaton concept was found in a Chinese text written in the 3rd century BC, while Computer Vision was born in the late 1960s. Therefore, visual perception applied to machines (i.e. the Machine Vision) is a young and exciting alliance. When robots came in, the new field of Robotic Vision was born, and these terms began to be erroneously interchanged. In short, we can say that Machine Vision is an engineering domain, which concern the industrial use of Vision. The Robotic Vision, instead, is a research field that tries to incorporate robotics aspects in computer vision algorithms. Visual Servoing, for example, is one of the problems that cannot be solved by computer vision only. Accordingly, a large part of this work deals with boosting popular Computer Vision techniques by exploiting robotics: e.g. the use of kinematics to localize a vision sensor, mounted as the robot end-effector. The remainder of this work is dedicated to the counterparty, i.e. the use of computer vision to solve real robotic problems like grasping objects or navigate avoiding obstacles. Will be presented a brief survey about mapping data structures most widely used in robotics along with SkiMap, a novel sparse data structure created both for robotic mapping and as a general purpose 3D spatial index. Thus, several approaches to implement Object Detection and Manipulation, by exploiting the aforementioned mapping strategies, will be proposed, along with a completely new Machine Teaching facility in order to simply the training procedure of modern Deep Learning networks.

Detecting social patterns within 20th century documentary photos: a deep learning based approach

The job of a historian is to understand what happened in the past, resorting in many cases to written documents as a firsthand source of information. Text, however, does not amount to the only source of knowledge. Pictorial representations, in fact, have also accompanied the main events of the historical timeline. In particular, the opportunity of visually representing circumstances has bloomed since the invention of photography, with the possibility of capturing in real-time the occurrence of a specific events. Thanks to the widespread use of digital technologies (e.g. smartphones and digital cameras), networking capabilities and consequent availability of multimedia content, the academic and industrial research communities have developed artificial intelligence (AI) paradigms with the aim of inferring, transferring and creating new layers of information from images, videos, etc. Now, while AI communities are devoting much of their attention to analyze digital images, from an historical research standpoint more interesting results may be obtained analyzing analog images representing the pre-digital era. Within the aforementioned scenario, the aim of this work is to analyze a collection of analog documentary photographs, building upon state-of-the-art deep learning techniques. In particular, the analysis carried out in this thesis aims at producing two following results: (a) produce the date of an image, and, (b) recognizing its background socio-cultural context,as defined by a group of historical-sociological researchers. Given these premises, the contribution of this work amounts to: (i) the introduction of an historical dataset including images of “Family Album” among all the twentieth century, (ii) the introduction of a new classification task regarding the identification of the socio-cultural context of an image, (iii) the exploitation of different deep learning architectures to perform the image dating and the image socio-cultural context classification.

End-to-end Deep Metric Learning con Vision-Language Model per il Fashion Image Captioning

L'image captioning è un task di machine learning che consiste nella generazione di una didascalia, o caption, che descriva le caratteristiche di un'immagine data in input. Questo può essere applicato, ad esempio, per descrivere in dettaglio i prodotti in vendita su un sito di e-commerce, migliorando l'accessibilità del sito web e permettendo un acquisto più consapevole ai clienti con difficoltà visive. La generazione di descrizioni accurate per gli articoli di moda online è importante non solo per migliorare le esperienze di acquisto dei clienti, ma anche per aumentare le vendite online. Oltre alla necessità di presentare correttamente gli attributi degli articoli, infatti, descrivere i propri prodotti con il giusto linguaggio può contribuire a catturare l'attenzione dei clienti. In questa tesi, ci poniamo l'obiettivo di sviluppare un sistema in grado di generare una caption che descriva in modo dettagliato l'immagine di un prodotto dell'industria della moda dato in input, sia esso un capo di vestiario o un qualche tipo di accessorio. A questo proposito, negli ultimi anni molti studi hanno proposto soluzioni basate su reti convoluzionali e LSTM. In questo progetto proponiamo invece un'architettura encoder-decoder, che utilizza il modello Vision Transformer per la codifica delle immagini e GPT-2 per la generazione dei testi. Studiamo inoltre come tecniche di deep metric learning applicate in end-to-end durante l'addestramento influenzino le metriche e la qualità delle caption generate dal nostro modello.

Supporting Scientific Research Through Machine and Deep Learning: Fluorescence Microscopy and Operational Intelligence Use Cases

Although the debate of what data science is has a long history and has not reached a complete consensus yet, Data Science can be summarized as the process of learning from data. Guided by the above vision, this thesis presents two independent data science projects developed in the scope of multidisciplinary applied research. The first part analyzes fluorescence microscopy images typically produced in life science experiments, where the objective is to count how many marked neuronal cells are present in each image. Aiming to automate the task for supporting research in the area, we propose a neural network architecture tuned specifically for this use case, cell ResUnet (c-ResUnet), and discuss the impact of alternative training strategies in overcoming particular challenges of our data. The approach provides good results in terms of both detection and counting, showing performance comparable to the interpretation of human operators. As a meaningful addition, we release the pre-trained model and the Fluorescent Neuronal Cells dataset collecting pixel-level annotations of where neuronal cells are located. In this way, we hope to help future research in the area and foster innovative methodologies for tackling similar problems. The second part deals with the problem of distributed data management in the context of LHC experiments, with a focus on supporting ATLAS operations concerning data transfer failures. In particular, we analyze error messages produced by failed transfers and propose a Machine Learning pipeline that leverages the word2vec language model and K-means clustering. This provides groups of similar errors that are presented to human operators as suggestions of potential issues to investigate. The approach is demonstrated on one full day of data, showing promising ability in understanding the message content and providing meaningful groupings, in line with previously reported incidents by human operators.

Concepts and methods for efficient decentralized learning in federated settings

Deep Neural Networks (DNNs) have revolutionized a wide range of applications beyond traditional machine learning and artificial intelligence fields, e.g., computer vision, healthcare, natural language processing and others. At the same time, edge devices have become central in our society, generating an unprecedented amount of data which could be used to train data-hungry models such as DNNs. However, the potentially sensitive or confidential nature of gathered data poses privacy concerns when storing and processing them in centralized locations. To this purpose, decentralized learning decouples model training from the need of directly accessing raw data, by alternating on-device training and periodic communications. The ability of distilling knowledge from decentralized data, however, comes at the cost of facing more challenging learning settings, such as coping with heterogeneous hardware and network connectivity, statistical diversity of data, and ensuring verifiable privacy guarantees. This Thesis proposes an extensive overview of decentralized learning literature, including a novel taxonomy and a detailed description of the most relevant system-level contributions in the related literature for privacy, communication efficiency, data and system heterogeneity, and poisoning defense. Next, this Thesis presents the design of an original solution to tackle communication efficiency and system heterogeneity, and empirically evaluates it on federated settings. For communication efficiency, an original method, specifically designed for Convolutional Neural Networks, is also described and evaluated against the state-of-the-art. Furthermore, this Thesis provides an in-depth review of recently proposed methods to tackle the performance degradation introduced by data heterogeneity, followed by empirical evaluations on challenging data distributions, highlighting strengths and possible weaknesses of the considered solutions. Finally, this Thesis presents a novel perspective on the usage of Knowledge Distillation as a mean for optimizing decentralized learning systems in settings characterized by data heterogeneity or system heterogeneity. Our vision on relevant future research directions close the manuscript.

Identificazione di caratteristiche rilevanti in capi di abbigliamento mediante deep-learning

Il mondo della moda è in continua e costante evoluzione, non solo dal punto di vista sociale, ma anche da quello tecnologico. Nel corso del presente elaborato si è studiata la possibilità di riconoscere e segmentare abiti presenti in una immagine utilizzando reti neurali profonde e approcci moderni. Sono state, quindi, analizzate reti quali FasterRCNN, MaskRCNN, YOLOv5, FashionPedia e Match-RCNN. In seguito si è approfondito l’addestramento delle reti neurali profonde in scenari di alta parallelizzazione e su macchine dotate di molteplici GPU al fine di ridurre i tempi di addestramento. Inoltre si è sperimentata la possibilità di creare una rete per prevedere se un determinato abito possa avere successo in futuro analizzando semplicemente dati passati e una immagine del vestito in questione. Necessaria per tali compiti è stata, inoltre, una approfondita analisi dei dataset esistenti nel mondo della moda e dei metodi per utilizzarli per l’addestramento. Il presente elaborato è stato svolto nell’ambito del progetto FA.RE.TRA. per il quale l'Università di Bologna svolge un compito di consulenza per lo studio di fattibilità su reti neurali in grado di svolgere i compiti menzionati.

On learning context-free and context-sensitive languages

The long short-term memory (LSTM) is not the only neural network which learns a context sensitive language. Second-order sequential cascaded networks (SCNs) are able to induce means from a finite fragment of a context-sensitive language for processing strings outside the training set. The dynamical behavior of the SCN is qualitatively distinct from that observed in LSTM networks. Differences in performance and dynamics are discussed.

Computer-aided recognition of dental implants in X-ray images

Dental implant recognition in patients without available records is a time-consuming and not straightforward task. The traditional method is a complete user-dependent process, where the expert compares a 2D X-ray image of the dental implant with a generic database. Due to the high number of implants available and the similarity between them, automatic/semi-automatic frameworks to aide implant model detection are essential. In this study, a novel computer-aided framework for dental implant recognition is suggested. The proposed method relies on image processing concepts, namely: (i) a segmentation strategy for semi-automatic implant delineation; and (ii) a machine learning approach for implant model recognition. Although the segmentation technique is the main focus of the current study, preliminary details of the machine learning approach are also reported. Two different scenarios are used to validate the framework: (1) comparison of the semi-automatic contours against implant’s manual contours of 125 X-ray images; and (2) classification of 11 known implants using a large reference database of 601 implants. Regarding experiment 1, 0.97±0.01, 2.24±0.85 pixels and 11.12±6 pixels of dice metric, mean absolute distance and Hausdorff distance were obtained, respectively. In experiment 2, 91% of the implants were successfully recognized while reducing the reference database to 5% of its original size. Overall, the segmentation technique achieved accurate implant contours. Although the preliminary classification results prove the concept of the current work, more features and an extended database should be used in a future work.

Adaptive learning in agents behaviour: A framework for electricity markets simulation

Electricity markets are complex environments, involving a large number of different entities, playing in a dynamic scene to obtain the best advantages and profits. MASCEM (Multi-Agent System for Competitive Electricity Markets) is a multi-agent electricity market simulator that models market players and simulates their operation in the market. Market players are entities with specific characteristics and objectives, making their decisions and interacting with other players. This paper presents a methodology to provide decision support to electricity market negotiating players. This model allows integrating different strategic approaches for electricity market negotiations, and choosing the most appropriate one at each time, for each different negotiation context. This methodology is integrated in ALBidS (Adaptive Learning strategic Bidding System) – a multiagent system that provides decision support to MASCEM's negotiating agents so that they can properly achieve their goals. ALBidS uses artificial intelligence methodologies and data analysis algorithms to provide effective adaptive learning capabilities to such negotiating entities. The main contribution is provided by a methodology that combines several distinct strategies to build actions proposals, so that the best can be chosen at each time, depending on the context and simulation circumstances. The choosing process includes reinforcement learning algorithms, a mechanism for negotiating contexts analysis, a mechanism for the management of the efficiency/effectiveness balance of the system, and a mechanism for competitor players' profiles definition.

Deteção Automática de Conteúdos Explícitos em Sequências de Vídeo

Nos últimos anos, o fácil acesso em termos de custos, ferramentas de produção, edição e distribuição de conteúdos audiovisuais, contribuíram para o aumento exponencial da produção diária deste tipo de conteúdos. Neste paradigma de superabundância de conteúdos multimédia existe uma grande percentagem de sequências de vídeo que contém material explícito, sendo necessário existir um controlo mais rigoroso, de modo a não ser facilmente acessível a menores. O conceito de conteúdo explícito pode ser caraterizado de diferentes formas, tendo o trabalho descrito neste documento incidido sobre a deteção automática de nudez feminina presente em sequências de vídeo. Este processo de deteção e classificação automática de material para adultos pode constituir uma ferramenta importante na gestão de um canal de televisão. Diariamente podem ser recebidas centenas de horas de material sendo impraticável a implementação de um processo manual de controlo de qualidade. A solução criada no contexto desta dissertação foi estudada e desenvolvida em torno de um produto especifico ligado à área do broadcasting. Este produto é o mxfSPEEDRAIL F1000, sendo este uma solução da empresa MOG Technologies. O objetivo principal do projeto é o desenvolvimento de uma biblioteca em C++, acessível durante o processo de ingest, que permita, através de uma análise baseada em funcionalidades de visão computacional, detetar e sinalizar na metadata do sinal, quais as frames que potencialmente apresentam conteúdo explícito. A solução desenvolvida utiliza um conjunto de técnicas do estado da arte adaptadas ao problema a tratar. Nestas incluem-se algoritmos para realizar a segmentação de pele e deteção de objetos em imagens. Por fim é efetuada uma análise critica à solução desenvolvida no âmbito desta dissertação de modo a que em futuros desenvolvimentos esta seja melhorada a nível do consumo de recursos durante a análise e a nível da sua taxa de sucesso.

Learning facial-expression models with crowdsourcing

The computational power is increasing day by day. Despite that, there are some tasks that are still difficult or even impossible for a computer to perform. For example, while identifying a facial expression is easy for a human, for a computer it is an area in development. To tackle this and similar issues, crowdsourcing has grown as a way to use human computation in a large scale. Crowdsourcing is a novel approach to collect labels in a fast and cheap manner, by sourcing the labels from the crowds. However, these labels lack reliability since annotators are not guaranteed to have any expertise in the field. This fact has led to a new research area where we must create or adapt annotation models to handle these weaklylabeled data. Current techniques explore the annotators’ expertise and the task difficulty as variables that influences labels’ correction. Other specific aspects are also considered by noisy-labels analysis techniques. The main contribution of this thesis is the process to collect reliable crowdsourcing labels for a facial expressions dataset. This process consists in two steps: first, we design our crowdsourcing tasks to collect annotators labels; next, we infer the true label from the collected labels by applying state-of-art crowdsourcing algorithms. At the same time, a facial expression dataset is created, containing 40.000 images and respective labels. At the end, we publish the resulting dataset.

The human eye as human-machine interface

Eye tracking as an interface to operate a computer is under research for a while and new systems are still being developed nowadays that provide some encouragement to those bound to illnesses that incapacitates them to use any other form of interaction with a computer. Although using computer vision processing and a camera, these systems are usually based on head mount technology being considered a contact type system. This paper describes the implementation of a human-computer interface based on a fully non-contact eye tracking vision system in order to allow people with tetraplegia to interface with a computer. As an assistive technology, a graphical user interface with special features was developed including a virtual keyboard to allow user communication, fast access to pre-stored phrases and multimedia and even internet browsing. This system was developed with the focus on low cost, user friendly functionality and user independency and autonomy.

Vision-based hand Wheel-chair control

Several studies have shown that people with disabilities benefit substantially from access to a means of independent mobility and assistive technology. Researchers are using technology originally developed for mobile robots to create easier to use wheelchairs. With this kind of technology people with disabilities can gain a degree of independence in performing daily life activities. In this work a computer vision system is presented, able to drive a wheelchair with a minimum number of finger commands. The user hand is detected and segmented with the use of a kinect camera, and fingertips are extracted from depth information, and used as wheelchair commands.

Aplicació de visió per dispositius mòbils

En aquest projecte es presenta l’aplicació per a dispositius mòbils Doppelganger. La seva funció és, a partir d’una fotografia, detectar la cara i mostrar la persona famosa de la nostra base de dades que més s’assembla a la persona en la fotografia. Per la implementació s’han utilitzat algoritmes de visió per computador i d’aprenentatge automàtic com per exemple el PCA i el K-Nearest Neighbor, tot utilitzant llibreries gratuïtes com són les OpenCV.