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: Visual Question Answering (VQA) is the task where given an image and a natural language question, the objective is to generate a natural language answer. At the intersection between computer vision and natural language processing, this task can be seen as a measure of image understanding capabilities, as it requires to reason about objects, actions, colors, positions, the relations between the different elements as well as commonsense reasoning, world knowledge, arithmetic skills and natural language understanding. However, even though the text present in the images conveys important semantically rich information that is explicit and not available in any other form, most VQA methods remained illiterate, largely
ignoring the text despite its potential significance. In this thesis, we set out on a journey to bring reading capabilities to computer vision models applied to the VQA task, creating new datasets and methods that can read, reason and integrate the text with other visual cues in natural scene images and documents.
In Chapter 3, we address the combination of scene text with visual information to fully understand all the nuances of natural scene images. To achieve this objective, we define a new sub-task of VQA that requires reading the text in the image, and highlight the limitations of the current methods. In addition, we propose a new architecture that integrates both modalities and jointly reasons about textual and visual features. In Chapter 5, we shift the domain of VQA with reading capabilities and apply it on scanned industry document images, providing a high-level end-purpose perspective to Document Understanding, which has been
primarily focused on digitizing the document’s contents and extracting key values without considering the ultimate purpose of the extracted information. For this, we create a dataset which requires methods to reason about the unique and challenging elements of documents, such as text, images, tables, graphs and complex layouts, to provide accurate answers in natural language. However, we observed that explicit visual features provide a slight contribution in the overall performance, since the main information is usually conveyed within the text and its position. In consequence, in Chapter 6, we propose VQA on infographic images, seeking for document images with more visually rich elements that require to fully exploit visual information in order to answer the questions. We show the performance gap of
different methods when used over industry scanned and infographic images, and propose a new method that integrates the visual features in early stages, which allows the transformer architecture to exploit the visual features during the self-attention operation. Instead, in Chapter 7, we apply VQA on a big collection of single-page documents, where the methods must find which documents are relevant to answer the question, and provide the answer itself. Finally, in Chapter 8, mimicking real-world application problems where systems must process documents with multiple pages, we address the multipage document visual question answering task. We demonstrate the limitations of existing methods, including models specifically designed to process long sequences. To overcome these limitations, we propose
a hierarchical architecture that can process long documents, answer questions, and provide the index of the page where the information to answer the question is located as an explainability measure.

Abstract: On-board pedestrian detection is crucial for Advanced Driver Assistance Systems
(ADAS). An accurate classication is fundamental for vision-based pedestrian detection.
The underlying assumption for learning classiers is that the training set and the deployment environment (testing) follow the same probability distribution regarding the features used by the classiers. However, in practice, there are dierent reasons that can break this constancy assumption. Accordingly, reusing existing classiers by adapting them from the previous training environment (source domain) to the new testing one (target domain) is an approach with increasing acceptance in the computer vision community. In this thesis we focus on the domain adaptation of deformable part-based models (DPMs) for pedestrian detection. As a prof of concept, we use a computer graphic based synthetic dataset, i.e. a virtual world, as the source domain, and adapt the virtual-world trained DPM detector to various real-world dataset.
We start by exploiting the maximum detection accuracy of the virtual-world
trained DPM. Even though, when operating in various real-world datasets, the virtualworld trained detector still suer from accuracy degradation due to the domain gap of virtual and real worlds. We then focus on domain adaptation of DPM. At the rst step, we consider single source and single target domain adaptation and propose two batch learning methods, namely A-SSVM and SA-SSVM. Later, we further consider leveraging multiple target (sub-)domains for progressive domain adaptation and propose a hierarchical adaptive structured SVM (HA-SSVM) for optimization. Finally, we extend HA-SSVM for the challenging online domain adaptation problem, aiming at making the detector to automatically adapt to the target domain online, without any human intervention. All of the proposed methods in this thesis do not require
revisiting source domain data. The evaluations are done on the Caltech pedestrian detection benchmark. Results show that SA-SSVM slightly outperforms A-SSVM and avoids accuracy drops as high as 15 points when comparing with a non-adapted detector. The hierarchical model learned by HA-SSVM further boosts the domain adaptation performance. Finally, the online domain adaptation method has demonstrated that it can achieve comparable accuracy to the batch learned models while not requiring manually label target domain examples. Domain adaptation for pedestrian detection is of paramount importance and a relatively unexplored area. We humbly hope the work in this thesis could provide foundations for future work in this area.

Abstract: Word spotting can be defined as the pattern recognition tasked aimed at locating and retrieving a specific keyword within a document image collection without explicitly transcribing the whole corpus. Its use is particularly interesting when applied in scenarios where Optical Character Recognition performs poorly or can not be used at all. This thesis focuses on such a scenario, word spotting on historical handwritten documents that have been written by a single author or by multiple authors with a similar calligraphy.
This problem requires a visual signature that is robust to image artifacts, flexible to accommodate script variations and efficient to retrieve information in a rapid manner. For this, we have developed a set of word spotting methods that on their foundation use the well known Bag-of-Visual-Words (BoVW) representation. This representation has gained popularity among the document image analysis community to characterize handwritten words
in an unsupervised manner. However, most approaches on this field rely on a basic BoVW configuration and disregard complex encoding and spatial representations. We determine which BoVW configurations provide the best performance boost to a spotting system.
Then, we extend the segmentation-based word spotting, where word candidates are given a priori, to segmentation-free spotting. The proposed approach seeds the document images with overlapping word location candidates and characterizes them with a BoVW signature. Retrieval is achieved comparing the query and candidate signatures and returning the locations that provide a higher consensus. This is a simple but powerful approach that requires a more compact signature than in a segmentation-based scenario. We first
project the BoVW signature into a reduced semantic topics space and then compress it further using Product Quantizers. The resulting signature only requires a few dozen bytes, allowing us to index thousands of pages on a common desktop computer. The final system still yields a performance comparable to the state-of-the-art despite all the information loss during the compression phases.
Afterwards, we also study how to combine different modalities of information in order to create a query-by-X spotting system where, words are indexed using an information modality and queries are retrieved using another. We consider three different information modalities: visual, textual and audio. Our proposal is to create a latent feature space where features which are semantically related are projected onto the same topics. Creating thus a new feature space where information from different modalities can be compared. Later, we consider the codebook generation and descriptor encoding problem. The codebooks used to encode the BoVW signatures are usually created using an unsupervised clustering algorithm and, they require to test multiple parameters to determine which configuration is best for a certain document collection. We propose a semantic clustering algorithm which allows to estimate the best parameter from data. Since gather annotated data is costly, we use synthetically generated word images. The resulting codebook is database agnostic, i. e. a codebook that yields a good performance on document collections that use the same script. We also propose the use of an additional codebook to approximate descriptors and reduce the descriptor encoding
complexity to sub-linear.
Finally, we focus on the problem of signatures dimensionality. We propose a new symbol probability signature where each bin represents the probability that a certain symbol is present a certain location of the word image. This signature is extremely compact and combined with compression techniques can represent word images with just a few bytes per signature.

Abstract: Recognizing object categories in real world images is a challenging problem in computer vision. The deformable part based framework is currently the most successful approach for object detection. Generally, HOG are used for image representation within the part-based framework. For action recognition, the bag-of-word framework has shown to provide promising results. Within the bag-of-words framework, local image patches are described by SIFT descriptor. Contrary to object detection and action recognition, combining color and shape has shown to provide the best performance for object and scene recognition.
In the first part of this thesis, we analyze the problem of person detection in still images. Standard person detection approaches rely on intensity based features for image representation while ignoring the color. Channel based descriptors is one of the most commonly used approaches in object recognition. This inspires us to evaluate incorporating color information using the channel based fusion approach for the task of person detection.
In the second part of the thesis, we investigate the problem of object detection in still images. Due to high dimensionality, channel based fusion increases the computational cost. Moreover, channel based fusion has been found to obtain inferior results for object category where one of the visual varies significantly. On the other hand, late fusion is known to provide improved results for a wide range of object categories. A consequence of late fusion strategy is the need of a pure color descriptor. Therefore, we propose to use Color attributes as an explicit color representation for object detection. Color attributes are compact and computationally efficient. Consequently color attributes are combined with traditional shape features providing excellent results for object detection task.
Finally, we focus on the problem of action detection and classification in still images. We investigate the potential of color for action classification and detection in still images. We also evaluate different fusion approaches for combining color and shape information for action recognition. Additionally, an analysis is performed to validate the contribution of color for action recognition. Our results clearly demonstrate that combining color and shape information significantly improve the performance of both action classification and detection in still images.

Abstract: In this work, we explore human action recognition and pose estimation prob-
lems. Different from traditional works of learning from 2D images or video
sequences and their annotated output, we seek to solve the problems with ad-
ditional 3D motion capture information, which helps to fill the gap between 2D
image features and human interpretations.
We first compare two different schools of approaches commonly used for 3D
pose estimation from 2D pose configuration: modeling and learning methods.
By looking into experiments results and considering our problems, we fixed a
learning method as the following approaches to do pose estimation. We then
establish a framework by adding a module of detecting 2D pose configuration
from images with varied background, which widely extend the application of
the approach. We also seek to directly estimate 3D poses from image features,
instead of estimating 2D poses as a intermediate module. We explore a robust
input feature, which combined with the proposed distance measure, provides
a solution for noisy or corrupted inputs. We further utilize the above method
to estimate weak poses,which is a concise representation of the original poses
by using dimension deduction technologies, from image features. Weak pose
space is where we calculate vocabulary and label action types using a bog of
words pipeline. Temporal information of an action is taken into consideration by
considering several consecutive frames as a single unit for computing vocabulary
and histogram assignments.

Abstract: Despite the “paperless office” ideal that started in the decade of the seventies, businesses still strive against an increasing amount of paper documentation. Companies still receive huge amounts of paper documentation that need to be analyzed and processed, mostly in a manual way. A solution for this task consists in, first, automatically scanning the incoming documents. Then, document images can be analyzed and information can be extracted from the data. Documents can also be automatically dispatched to the appropriate workflows, used to retrieve similar documents in the dataset to transfer information, etc.
Due to the nature of this “digital mailroom”, we need document representation methods to be general, i.e., able to cope with very different types of documents. We need the methods to be sound, i.e., able to cope with unexpected types of documents, noise, etc. And, we need to methods to be scalable, i.e., able to cope with thousands or millions of documents that need to be processed, stored, and consulted. Unfortunately, current techniques of document representation, classification and retrieval are not apt for this digital mailroom framework, since they do not fulfill some or all of these requirements.
Through this thesis we focus on the problem of document representation aimed at classification and retrieval tasks under this digital mailroom framework. We first propose a novel document representation based on runlength histograms, and extend it to cope with more complex documents such as multiple-page documents, or documents that contain more sources of information such as extracted OCR text. Then we focus on the scalability requirements and propose a novel binarization method which we dubbed PCAE, as well as two general asymmetric distances between binary embeddings that can significantly improve the retrieval results at a minimal extra computational cost. Finally, we note the importance of supervised learning when performing large-scale retrieval, and study several approaches that can significantly boost the results at no extra cost at query time.