Abstract: Machine learning experimentation under controlled scenarios and standard datasets is necessary to compare algorithms performance by evaluating all of them in the same setup. However, experimentation on how those algorithms perform on unconstrained data and applied tasks to solve real world problems is also a must to ascertain how that research can contribute to our society.
In this dissertation we experiment with the latest computer vision and natural language processing algorithms applying them to multimodal scene interpretation. Particularly, we research on how image and text understanding can be jointly exploited to address real world problems, focusing on learning from Social Media data.
We address several tasks that involve image and textual information, discuss their characteristics and offer our experimentation conclusions. First, we work on detection of scene text in images. Then, we work with Social Media posts, exploiting the captions associated to images as supervision to learn visual features, which we apply to multimodal semantic image retrieval. Subsequently, we work with geolocated Social Media images with associated tags, experimenting on how to use the tags as supervision, on location sensitive image retrieval and on exploiting location information for image tagging. Finally, we work on a specific classification problem of Social Media publications consisting on an image and a text: Multimodal hate speech classification.

Abstract: Image generation is arguably one of the most attractive, compelling, and challenging tasks in computer vision. Among the methods which perform image generation, generative adversarial networks (GANs) play a key role. The most common image generation models based on GANs can be divided into two main approaches. The first one, called simply image generation takes random noise as an input and synthesizes an image which follows the same distribution as the images in the training set. The second class, which is called image-to-image translation, aims to map an image from a source domain to one that is indistinguishable from those in the target domain. Image-to-image translation methods can further be divided into paired and unpaired image-to-image translation based on whether they require paired data or not. In this thesis, we aim to address some challenges of both image generation and image-to-image generation.GANs highly rely upon having access to vast quantities of data, and fail to generate realistic images from random noise when applied to domains with few images. To address this problem, we aim to transfer knowledge from a model trained on a large dataset (source domain) to the one learned on limited data (target domain). We find that both GANs andconditional GANs can benefit from models trained on large datasets. Our experiments show that transferring the discriminator is more important than the generator. Using both the generator and discriminator results in the best performance. We found, however, that this method suffers from overfitting, since we update all parameters to adapt to the target data. We propose a novel architecture, which is tailored to address knowledge transfer to very small target domains. Our approach effectively exploreswhich part of the latent space is more related to the target domain. Additionally, the proposed method is able to transfer knowledge from multiple pretrained GANs. Although image-to-image translation has achieved outstanding performance, it still facesseveral problems. First, for translation between complex domains (such as translations between different modalities) image-to-image translation methods require paired data. We show that when only some of the pairwise translations have been seen (i.e. during training), we can infer the remaining unseen translations (where training pairs are not available). We propose a new approach where we align multiple encoders and decoders in such a way that the desired translation can be obtained by simply cascadingthe source encoder and the target decoder, even when they have not interacted during the training stage (i.e. unseen). Second, we address the issue of bias in image-to-image translation. Biased datasets unavoidably contain undesired changes, which are dueto the fact that the target dataset has a particular underlying visual distribution. We use carefully designed semantic constraints to reduce the effects of the bias. The semantic constraint aims to enforce the preservation of desired image properties. Finally, current approaches fail to generate diverse outputs or perform scalable image transfer in a single model. To alleviate this problem, we propose a scalable and diverse image-to-image translation. We employ random noise to control the diversity. The scalabitlity is determined by conditioning the domain label.computer vision, deep learning, imitation learning, adversarial generative networks, image generation, image-to-image translation.

Abstract: One of the fundamental problems of computer vision is to represent images with compact semantically relevant embeddings. These embeddings could then be used in a wide variety of applications, such as image retrieval, object detection, and video search. The main objective of this thesis is to study image embeddings from two aspects: color embeddings and deep embeddings.
In the first part of the thesis we start from hand-crafted color embeddings. We propose a method to order the additional color names according to their complementary nature with the basic eleven color names. This allows us to compute color name representations with high discriminative power of arbitrary length. Psychophysical experiments confirm that our proposed method outperforms baseline approaches. Secondly, we learn deep color embeddings from weakly labeled data by adding an attention strategy. The attention branch is able to correctly identify the relevant regions for each class. The advantage of our approach is that it can learn color names for specific domains for which no pixel-wise labels exists.
In the second part of the thesis, we focus on deep embeddings. Firstly, we address the problem of compressing large embedding networks into small networks, while maintaining similar performance. We propose to distillate the metrics from a teacher network to a student network. Two new losses are introduced to model the communication of a deep teacher network to a small student network: one based on an absolute teacher, where the student aims to produce the same embeddings as the teacher, and one based on a relative teacher, where the distances between pairs of data points is communicated from the teacher to the student. In addition, various aspects of distillation have been investigated for embeddings, including hint and attention layers, semi-supervised learning and cross quality distillation. Finally, another aspect of deep metric learning, namely lifelong learning, is studied. We observed some drift occurs during training of new tasks for metric learning. A method to estimate the semantic drift based on the drift which is experienced by data of the current task during its training is introduced. Having this estimation, previous tasks can be compensated for this drift, thereby improving their performance. Furthermore, we show that embedding networks suffer significantly less from catastrophic forgetting compared to classification networks when learning new tasks.

Abstract: Lung cancer is one of the most diagnosed cancers among men and women. Actually,
lung cancer accounts for 13% of the total cases with a 5-year global survival
rate in patients. Although Early detection increases survival rate from 38% to 67%, accurate diagnosis remains a challenge. Pathological confirmation requires extracting a sample of the lesion tissue for its biopsy. The preferred procedure for tissue biopsy is called bronchoscopy. A bronchoscopy is an endoscopic technique for the internal exploration of airways which facilitates the performance of minimal invasive interventions with low risk for the patient. Recent advances in bronchoscopic devices have increased their use for minimal invasive diagnostic and intervention procedures, like lung cancer biopsy sampling. Despite the improvement in bronchoscopic device quality, there is a lack of intelligent computational systems for supporting in-vivo clinical decision during examinations. Existing technologies fail to accurately reach the lesion due to several aspects at intervention off-line planning and poor intra-operative guidance at exploration time. Existing guiding systems radiate patients and clinical staff,might be expensive and achieve a suboptimlal 70% of yield boost. Diagnostic yield could be improved reducing radiation and costs by developing intra-operative support systems able to guide the bronchoscopist to the lesion during the intervention. The goal of this PhD thesis is to develop an image-based navigation systemfor intra-operative guidance of bronchoscopists to a target lesion across a path previously planned on a CT-scan. We propose a 3D navigation system which uses the anatomy of video bronchoscopy frames to locate the bronchoscope within the airways. Once the bronchoscope is located, our navigation system is able to indicate the bifurcation which needs to be followed to reach the lesion. In order to facilitate an off-line validation
as realistic as possible, we also present a method for augmenting simulated virtual bronchoscopies with the appearance of intra-operative videos. Experiments performed on augmented and intra-operative videos, prove that our algorithm can be speeded up for an on-line implementation in the operating room.

Abstract: Optical flow has got a major role in making advanced driver assistance systems (ADAS) a reality. ADAS applications are expected to perform efficiently in all kinds of environments, those are highly probable, that one can drive the vehicle in different kinds of roads, times and seasons. In this work, we study the relationship of optical flow with different roads, that is by analyzing optical flow accuracy on different road textures. Texture measures such as TeX , TeX and TeX are evaluated for this purpose. Further, the relation of regularization weight to the flow accuracy in the presence of different textures is also analyzed. Additionally, we present a framework to generate synthetic sequences of different textures in ADAS scenarios with ground-truth optical flow.

Abstract: This thesis embarks on an exploratory journey into robustness in deep learning,
with a keen focus on the intertwining facets of generalization, explainability, and
edge cases within the realm of computer vision. In deep learning, robustness
epitomizes a model’s resilience and flexibility, grounded on its capacity to generalize across diverse data distributions, explain its predictions transparently, and navigate the intricacies of edge cases effectively. The challenges associated with robust generalization are multifaceted, encompassing the model’s performance on unseen data and its defense against out-of-distribution data and adversarial attacks. Bridging this gap, the potential of Embedding Propagation (EP) for improving out-of-distribution generalization is explored. EP is depicted as a powerful tool facilitating manifold smoothing, which in turn fortifies the model’s robustness against adversarial onslaughts and bolsters performance in few-shot and self-/semi-supervised learning scenarios. In the labyrinth of deep learning models, the path to robustness often intersects with explainability. As model complexity increases, so does the urgency to decipher their decision-making
processes. Acknowledging this, the thesis introduces a robust framework for
evaluating and comparing various counterfactual explanation methods, echoing
the imperative of explanation quality over quantity and spotlighting the intricacies of diversifying explanations. Simultaneously, the deep learning landscape is fraught with edge cases – anomalies in the form of small objects or rare instances in object detection tasks that defy the norm. Confronting this, the
thesis presents an extension of the DETR (DEtection TRansformer) model to enhance small object detection. The devised DETR-FP, embedding the Feature Pyramid technique, demonstrating improvement in small objects detection accuracy, albeit facing challenges like high computational costs. With emergence of foundation models in mind, the thesis unveils EarthView, the largest scale remote sensing dataset to date, built for the self-supervised learning of a robust foundational model for remote sensing. Collectively, these studies contribute to the grand narrative of robustness in deep learning, weaving together the strands of generalization, explainability, and edge case performance. Through these methodological advancements and novel datasets, the thesis calls for continued exploration, innovation, and refinement to fortify the bastion of robust computer vision.

Abstract: The Baix Llobregat (BALL) Demographic Database is an ongoing database project containing individual census data from the Catalan region of Baix Llobregat (Spain) during the nineteenth and twentieth centuries. The BALL Database is built within the project ‘NETWORKS: Technology and citizen innovation for building historical social networks to understand the demographic past’ directed by Alícia Fornés from the Center for Computer Vision and Joana Maria Pujadas-Mora from the Center for Demographic Studies, both at the Universitat Autònoma de Barcelona, funded by the Recercaixa program (2017–2019).
Its webpage is http://dag.cvc.uab.es/xarxes/.The aim of the project is to develop technologies facilitating massive digitalization of demographic sources, and more specifically the padrones (local censuses), in order to reconstruct historical ‘social’ networks employing computer vision technology. Such virtual networks can be created thanks to the linkage of nominative records compiled in the local censuses across time and space. Thus, digitized versions of individual and family lifespans are established, and individuals and families can be located spatially.

Abstract: This paper defines an intelligent and interactive framework to classify multiple regions of interest from the original data on demand, without requiring any preprocessing or previous segmentation. The proposed intelligent and interactive approach is divided in three stages: visualize, training and testing. First, users visualize and label some samples directly on slices of the volume. Training and testing are based on a framework of Error Correcting Output Codes and Adaboost classifiers that learn to classify each region the user has painted. Later, at the testing stage, each classifier is directly applied on the rest of samples and combined to perform multi-class labeling, being used in the final rendering. We also parallelized the training stage using a GPU-based implementation for
obtaining a rapid interaction and classification.