Publications

The problem of prostate segmentation from Magnetic Resonance Imaging (MRI) is an intense research area, due to the increased use of MRI in the diagnosis and treatment planning of prostate cancer. The lack of clear boundaries and huge variation of texture and shapes between patients makes the task very challenging, and the 3D nature of the data makes 2D segmentation algorithms suboptimal for the task. With this paper, we propose a novel architecture to fill the gap between the most recent advances in 2D computer vision and 3D semantic segmentation. In particular, the designed model retrieves multi-scale 3D features with dilated convolutions and makes use of a self-attention transformer to gain a global field of view. The proposed Long-Range 3D Self-Attention block allows the convolutional neural network to build significant features by merging together contextual information collected at various scales. Experimental results show that the proposed method improves the state-of-the-art segmentation accuracy on MRI prostate segmentation.

Nell'ultimo decennio, il Deep Learning è diventato un argomento caldo oltre che uno strumento dirompente nel contesto del Machine Learning e della Computer Vision. Si basa su un paradigma di apprendimento in cui i dati (ad esempio, i video acquisiti da telecamere di video-sorveglianza poste su una strada pubblica) giocano un ruolo cruciale. Sfruttando un gran numero di esempi, è possibile imparare compiti complessi e simili a quelli svolti da esseri umani (ad esempio, riconoscere azioni anomale in un video-stream) con risultati impressionanti. Tuttavia, se la disponibilità di dati rappresenta la più grande forza delle tecniche di Deep Learning, essa nasconde anche la più grande debolezza: lo sviluppo di applicazioni e servizi è, infatti, spesso limitato da tale requisito, poiché l'acquisizione e il mantenimento di una enorme quantità di dati sono attività costose che richiedono personale esperto e attrezzature idonee. Tuttavia, la progettazione delle moderne architetture di Deep Learning offre diversi gradi di libertà, i quali possono essere sfruttati per mitigare la mancanza di dati di allenamento, sia essa parziale che completa. L'idea di fondo è quella di compensare tale mancanza incorporando una conoscenza preliminare che gli umani (in particolare, colore che controllano e guidano il processo di apprendimento) detengono sul dominio in questione. Infatti, le regole e le proprietà intrinseche si estendono ben oltre i dati di formazione e spesso possono essere identificate e imposte al modello di learning. Se prendiamo in considerazione la classificazione delle immagini, il successo delle Reti Neurali Convoluzionali (CNN) rispetto alle soluzioni del passato (come le Reti Neurali Multistrato) può essere attribuito principalmente a tale pratica. Infatti, i principi di progettazione del suo elemento costitutivo fondamentale (cioè la convoluzione tra due segnali 2D) riflettono naturalmente ciò che sapevamo sulle immagini naturali: le correlazioni che sussistono tra le regioni vicine dell'immagine hanno fornito pertanto una potente intuizione per lo sviluppo di modelli efficienti ed efficaci come lo sono ancora le CNN. Lo scopo di questa tesi riguarda l'indagine e la proposta di nuovi modi di modellare e iniettare la conoscenza a priori nelle architetture di Deep Learning. È importante sottolineare che tale discussione è trasversale: infatti, si concentra su diversi domini di dati (ad esempio, immagini, video, dati strutturati mediante un grafo, ecc.) e coinvolge diversi livelli della pipeline complessiva. Su quest'ultimo punto, il lettore viene guidato in questa ricerca attraverso la seguente triplice categorizzazione: i) approcci basati sui parametri, che limitano lo spazio delle soluzioni possibili a quelle regioni che riflettono le proprietà geometriche dei dati; ii) approcci goal-driven, che guidano il processo di apprendimento verso soluzioni che incarnano alcune proprietà vantaggiose; iii) approcci data-driven, che sfruttano i dati per estrarre la conoscenza da utilizzare successivamente per condizionare l'algoritmo di training. Insieme a una descrizione completa di entrambe le impostazioni e degli strumenti coinvolti, presentiamo ampi risultati sperimentali e studi di ablazione che dimostrano il valore delle tecniche proposte in questa ricerca.

The power produced by a wind turbine depends on environmental conditions, working parameters, and interactions with nearby turbines. However, these aspects are often neglected in the design of data-driven models for wind farms' performance analysis. In this article, we propose to predict the active power and to provide reliable prediction intervals via ensembles of multivariate polynomial regression models that exploit a higher number of inputs (compared to most approaches in the literature), including operational and thermal variables. We present two main strategies: the former considers the environmental measurements collected at the other wind turbines in the farm as additional modeling information for the turbine under analysis; the latter combines multiple models relative to different operative conditions. We validate our approach on real data from the SCADA system of a wind farm in Italy and obtain a MAE of the order of 1.0% of the rated power of the turbine. Moreover, due to the structure of our approach, we can gain quantitative insights on the covariates most frequently selected depending on the working region of the wind turbines.

Embodied agents, trained to explore and navigate indoor photorealistic environments, have achieved impressive results on standard datasets and benchmarks. So far, experiments and evaluations have involved domestic and working scenes like offices, flats, and houses. In this paper, we build and release a new 3D space with unique characteristics: the one of a complete art museum. We name this environment ArtGallery3D (AG3D). Compared with existing 3D scenes, the collected space is ampler, richer in visual features, and provides very sparse occupancy information. This feature is challenging for occupancy-based agents which are usually trained in crowded domestic environments with plenty of occupancy information. Additionally, we annotate the coordinates of the main points of interest inside the museum, such as paintings, statues, and other items. Thanks to this manual process, we deliver a new benchmark for PointGoal navigation inside this new space. Trajectories in this dataset are far more complex and lengthy than existing ground-truth paths for navigation in Gibson and Matterport3D. We carry on extensive experimental evaluation using our new space for evaluation and prove that existing methods hardly adapt to this scenario. As such, we believe that the availability of this 3D model will foster future research and help improve existing solutions.

In this paper, we present novel strategies for optimizing the performance of many binary image processing algorithms. These strategies are collected in an open-source framework, GRAPHGEN, that is able to automatically generate optimized C++ source code implementing the desired optimizations. Simply starting from a set of rules, the algorithms introduced with the GRAPHGEN framework can generate decision trees with minimum average path-length, possibly considering image pattern frequencies, apply state prediction and code compression by the use of Directed Rooted Acyclic Graphs (DRAGs). Moreover, the proposed algorithmic solutions allow to combine different optimization techniques and significantly improve performance. Our proposal is showcased on three classical and widely employed algorithms (namely Connected Components Labeling, Thinning, and Contour Tracing). When compared to existing approaches —in 2D and 3D—, implementations using the generated optimal DRAGs perform significantly better than previous state-of-the-art algorithms, both on CPU and GPU.

Visual perception from drones has been largely investigated for Intelligent Traffic Monitoring System (ITMS) recently. In this paper, we introduce SeeFar to achieve vehicle speed estimation and traffic flow analysis based on YOLOv5 and DeepSORT from a moving drone. SeeFar differs from previous works in three key ways: the speed estimation and flow analysis components are integrated into a unified framework; our method of predicting car speed has the least constraints while maintaining a high accuracy; our flow analysor is direction-aware and outlier-aware. Specifically, we design the speed estimator only using the camera imaging geometry, where the transformation between world space and image space is completed by the variable Ground Sampling Distance. Besides, previous papers do not evaluate their speed estimators at scale due to the difficulty of obtaining the ground truth, we therefore propose a simple yet efficient approach to estimate the true speeds of vehicles via the prior size of the road signs. We evaluate SeeFar on our ten videos that contain 929 vehicle samples. Experiments on these sequences demonstrate the effectiveness of SeeFar by achieving 98.0% accuracy of speed estimation and 99.1% accuracy of traffic volume prediction, respectively.

Vision Transformers (ViT) and other Transformer-based architectures for image classification have achieved promising performances in the last two years. However, ViT-based models require large datasets, memory, and computational power to obtain state-of-the-art results compared to more traditional architectures. The generic ViT model, indeed, maintains a full-length patch sequence during inference, which is redundant and lacks hierarchical representation. With the goal of increasing the efficiency of Transformer-based models, we explore the application of a 2D max-pooling operator on the outputs of Transformer encoders. We conduct extensive experiments on the CIFAR-100 dataset and the large ImageNet dataset and consider both accuracy and efficiency metrics, with the final goal of reducing the token sequence length without affecting the classification performance. Experimental results show that bidimensional downsampling can outperform previous classification approaches while requiring relatively limited computation resources.

Image captioning models aim at connecting Vision and Language by providing natural language descriptions of input images. In the past few years, the task has been tackled by learning parametric models and proposing visual feature extraction advancements or by modeling better multi-modal connections. In this paper, we investigate the development of an image captioning approach with a kNN memory, with which knowledge can be retrieved from an external corpus to aid the generation process. Our architecture combines a knowledge retriever based on visual similarities, a differentiable encoder, and a kNN-augmented attention layer to predict tokens based on the past context and on text retrieved from the external memory. Experimental results, conducted on the COCO dataset, demonstrate that employing an explicit external memory can aid the generation process and increase caption quality. Our work opens up new avenues for improving image captioning models at larger scale.