Abstract: This work compares Single Shot MultiBox Detector (SSD) and You Only Look Once (YOLO) deep neural networks for the outdoor advertisement panel detection problem by handling multiple and combined variabilities in the scenes. Publicity panel detection in images offers important advantages both in the real world as well as in the virtual one. For example, applications like Google Street View can be used for Internet publicity and when detecting these ads panels in images, it could be possible to replace the publicity appearing inside the panels by another from a funding company. In our experiments, both SSD and YOLO detectors have produced acceptable results under variable sizes of panels, illumination conditions, viewing perspectives, partial occlusion of panels, complex background and multiple panels in scenes. Due to the difficulty of finding annotated images for the considered problem, we created our own dataset for conducting the experiments. The major strength of the SSD model was the almost elimination of False Positive (FP) cases, situation that is preferable when the publicity contained inside the panel is analyzed after detecting them. On the other side, YOLO produced better panel localization results detecting a higher number of True Positive (TP) panels with a higher accuracy. Finally, a comparison of the two analyzed object detection models with different types of semantic segmentation networks and using the same evaluation metrics is also included.

Abstract: Word spotting is an important recognition task in large-scale retrieval of document collections. In most of the cases, methods are developed and evaluated assuming perfect word segmentation. In this paper, we propose an experimental framework to quantify the goodness that word segmentation has on the performance achieved by word spotting methods in identical unbiased conditions. The framework consists of generating systematic distortions on segmentation and retrieving the original queries from the distorted dataset. We have tested our framework on several established and state-of-the-art methods using George Washington and Barcelona Marriage Datasets. The experiments done allow for an estimate of the end-to-end performance of word spotting methods.

Abstract: JCR 2019 Q2, IF=3.121
The task of unpaired image-to-image translation is highly challenging due to the lack of explicit cross-domain pairs of instances. We consider here diverse image translation (DIT), an even more challenging setting in which an image can have multiple plausible translations. This is normally achieved by explicitly disentangling content and style in the latent representation and sampling different styles codes while maintaining the image content. Despite the success of current DIT models, they are prone to suffer from bias. In this paper, we study the problem of bias in image-to-image translation. Biased datasets may add undesired changes (e.g. change gender or race in face images) to the output translations as a consequence of the particular underlying visual distribution in the target domain. In order to alleviate the effects of this problem we propose the use of semantic constraints that enforce the preservation of desired image properties. Our proposed model is a step towards unbiased diverse image-to-image translation (UDIT), and results in less unwanted changes in the translated images while still performing the wanted transformation. Experiments on several heavily biased datasets show the effectiveness of the proposed techniques in different domains such as faces, objects, and scenes.

Abstract: Depth information is essential for on-board perception in autonomous driving and driver assistance. Monocular depth estimation (MDE) is very appealing since it allows for appearance and depth being on direct pixelwise correspondence without further calibration. Best MDE models are based on Convolutional Neural Networks (CNNs) trained in a supervised manner, i.e., assuming pixelwise ground truth (GT). Usually, this GT is acquired at training time through a calibrated multi-modal suite of sensors. However, also using only a monocular system at training time is cheaper and more scalable. This is possible by relying on structure-from-motion (SfM) principles to generate self-supervision. Nevertheless, problems of camouflaged objects, visibility changes, static-camera intervals, textureless areas, and scale ambiguity, diminish the usefulness of such self-supervision. In this paper, we perform monocular depth estimation by virtual-world supervision (MonoDEVS) and real-world SfM self-supervision. We compensate the SfM self-supervision limitations by leveraging virtual-world images with accurate semantic and depth supervision and addressing the virtual-to-real domain gap. Our MonoDEVSNet outperforms previous MDE CNNs trained on monocular and even stereo sequences.

Abstract: Outlier, or anomaly, detection is essential for optimal performance of machine learning methods and statistical predictive models. It is not just a technical step in a data cleaning process but a key topic in many fields such as fraudulent document detection, in medical applications and assisted diagnosis systems or detecting security threats. In contrast to population-based methods, neighborhood based local approaches are simple flexible methods that have the potential to perform well in small sample size unbalanced problems. However, a main concern of local approaches is the impact that the computation of each sample neighborhood has on the method performance. Most approaches use a distance in the feature space to define a single neighborhood that requires careful selection of several parameters. This work presents a local approach based on a local measure of the heterogeneity of sample labels in the feature space considered as a topological manifold. Topology is computed using the communities of a weighted graph codifying mutual nearest neighbors in the feature space. This way, we provide with a set of multiple neighborhoods able to describe the structure of complex spaces without parameter fine tuning. The extensive experiments on real-world data sets show that our approach overall outperforms, both, local and global strategies in multi and single view settings.

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: Computer vision has gone through considerable changes in the last decade as neural networks have come into common use. As available computational capabilities have grown, neural networks have achieved breakthroughs in many computer vision tasks, and have even surpassed human performance in others. With accuracy being so high, focus has shifted to other issues and challenges. One research direction that saw a notable increase in interest is on lifelong learning systems. Such systems should be capable of efficiently performing tasks, identifying and learning new ones, and should moreover be able to deploy smaller versions of themselves which are experts on specific tasks. In this thesis, we contribute to research on lifelong learning and address the compression and adaptation of networks to small target domains, the incremental learning of networks faced with a variety of tasks, and finally the detection of out-of-distribution samples at inference time.
We explore how knowledge can be transferred from large pretrained models to more task-specific networks capable of running on smaller devices by extracting the most relevant information. Using a pretrained model provides more robust representations and a more stable initialization when learning a smaller task, which leads to higher performance and is known as domain adaptation. However, those models are too large for certain applications that need to be deployed on devices with limited memory and computational capacity. In this thesis we show that, after performing domain adaptation, some learned activations barely contribute to the predictions of the model. Therefore, we propose to apply network compression based on low-rank matrix decomposition using the activation statistics. This results in a significant reduction of the model size and the computational cost.
Like human intelligence, machine intelligence aims to have the ability to learn and remember knowledge. However, when a trained neural network is presented with learning a new task, it ends up forgetting previous ones. This is known as catastrophic forgetting and its avoidance is studied in continual learning. The work presented in this thesis extensively surveys continual learning techniques and presents an approach to avoid catastrophic forgetting in sequential task learning scenarios. Our technique is based on using ternary masks in order to update a network to new tasks, reusing the knowledge of previous ones while not forgetting anything about them. In contrast to earlier work, our masks are applied to the activations of each layer instead of the weights. This considerably reduces the number of parameters to be added for each new task. Furthermore, the analysis on a wide range of work on incremental learning without access to the task-ID, provides insight on current state-of-the-art approaches that focus on avoiding catastrophic forgetting by using regularization, rehearsal of previous tasks from a small memory, or compensating the task-recency bias.
Neural networks trained with a cross-entropy loss force the outputs of the model to tend toward a one-hot encoded vector. This leads to models being too overly confident when presented with images or classes that were not present in the training distribution. The capacity of a system to be aware of the boundaries of the learned tasks and identify anomalies or classes which have not been learned yet is key to lifelong learning and autonomous systems. In this thesis, we present a metric learning approach to out-of-distribution detection that learns the task at hand on an embedding space.

Abstract: Sectors as fintech, legaltech or insurance process an inflow of millions of forms, invoices, id documents, claims or similar every day. Together with these, historical archives provide gigantic amounts of digitized documents containing useful information that needs to be stored in machine encoded text with a meaningful structure. This procedure, known as information extraction (IE) comprises the steps of localizing and recognizing text, identifying named entities contained in it and optionally finding relationships among its elements. In this work we explore multi-task neural models at image and graph level to solve all steps in a unified way. While doing so we find benefits and limitations of these end-to-end approaches in comparison with sequential separate methods. More specifically, we first propose a method to produce textual as well as semantic labels with a unified model from handwritten text line images. We do so with the use of a convolutional recurrent neural model trained with connectionist temporal classification to predict the textual as well as semantic information encoded in the images. Secondly, motivated by the success of this approach we investigate the unification of the localization and recognition tasks of handwritten text in full pages with an end-to-end model, observing benefits in doing so. Having two models that tackle information extraction subsequent task pairs in an end-to-end to end manner, we lastly contribute with a method to put them all together in a single neural network to solve the whole information extraction pipeline in a unified way. Doing so we observe some benefits and some limitations in the approach, suggesting that in certain cases it is beneficial to train specialized models that excel at a single challenging task of the information extraction process, as it can be the recognition of named entities or the extraction of relationships between them. For this reason we lastly study the use of the recently arrived graph neural network architectures for the semantic tasks of the information extraction process, which are recognition of named entities and relation extraction, achieving promising results on the relation extraction part.