Abstract: Current tasks and methods in Document Understanding aims to process documents as single elements. However, documents are usually organized in collections (historical records, purchase invoices), that provide context useful for their interpretation. To address this problem, we introduce Document Collection Visual Question Answering (DocCVQA) a new dataset and related task, where questions are posed over a whole collection of document images and the goal is not only to provide the answer to the given question, but also to retrieve the set of documents that contain the information needed to infer the answer. Along with the dataset we propose a new evaluation metric and baselines which provide further insights to the new dataset and task.

Abstract: Historical ciphered manuscripts are a type of document where graphical symbols are used to encrypt their content instead of regular text. Nowadays, expert transcriptions can be found in libraries alongside the corresponding manuscript images. However, those transcriptions are not aligned, so these are barely usable for training deep learning-based recognition methods. To solve this issue, we propose a method to align each symbol in the transcript of an image with its visual representation by using an attention-based Sequence to Sequence (Seq2Seq) model. The core idea is that, by learning to recognise symbols sequence within a cipher line image, the model also identifies their position implicitly through an attention mechanism. Thus, the resulting symbol segmentation can be later used for training algorithms. The experimental evaluation shows that this method is promising, especially taking into account the small size of the cipher dataset.

Abstract: Session-based recommenders, used for making predictions out of users’ uninterrupted sequences of actions, are attractive for many applications. Here, for this task we propose using metric learning, where a common embedding space for sessions and items is created, and distance measures dissimilarity between the provided sequence of users’ events and the next action. We discuss and compare metric learning approaches to commonly used learning-to-rank methods, where some synergies exist. We propose a simple architecture for problem analysis and demonstrate that neither extensively big nor deep architectures are necessary in order to outperform existing methods. The experimental results against strong baselines on four datasets are provided with an ablation study.

Abstract: Manually annotating images to develop vision models has been a major bottleneck
since computer vision and machine learning started to walk together. This has
been more evident since computer vision falls on the shoulders of data-hungry
deep learning techniques. When addressing on-board perception for autonomous
driving, the curse of data annotation is exacerbated due to the use of additional
sensors such as LiDAR. Therefore, any approach aiming at reducing such a timeconsuming and costly work is of high interest for addressing autonomous driving
and, in fact, for any application requiring some sort of artificial perception. In the
last decade, it has been shown that leveraging from synthetic data is a paradigm
worth to pursue in order to minimizing manual data annotation. The reason is
that the automatic process of generating synthetic data can also produce different
types of associated annotations (e.g. object bounding boxes for synthetic images
and LiDAR pointclouds, pixel/point-wise semantic information, etc.). Directly
using synthetic data for training deep perception models may not be the definitive
solution in all circumstances since it can appear a synth-to-real domain shift. In
this context, this work focuses on leveraging synthetic data to alleviate manual
annotation for three perception tasks related to driving assistance and autonomous
driving. In all cases, we assume the use of deep convolutional neural networks
(CNNs) to develop our perception models.
The first task addresses traffic sign recognition (TSR), a kind of multi-class
classification problem. We assume that the number of sign classes to be recognized
must be suddenly increased without having annotated samples to perform the
corresponding TSR CNN re-training. We show that leveraging synthetic samples of
such new classes and transforming them by a generative adversarial network (GAN)
trained on the known classes (i.e. without using samples from the new classes), it is
possible to re-train the TSR CNN to properly classify all the signs for a ∼ 1/4 ratio of
new/known sign classes. The second task addresses on-board 2D object detection,
focusing on vehicles and pedestrians. In this case, we assume that we receive a set
of images without the annotations required to train an object detector, i.e. without
object bounding boxes. Therefore, our goal is to self-annotate these images so
that they can later be used to train the desired object detector. In order to reach
this goal, we leverage from synthetic data and propose a semi-supervised learning
approach based on the co-training idea. In fact, we use a GAN to reduce the synthto-real domain shift before applying co-training. Our quantitative results show
that co-training and GAN-based image-to-image translation complement each
other up to allow the training of object detectors without manual annotation, and still almost reaching the upper-bound performances of the detectors trained from
human annotations. While in previous tasks we focus on vision-based perception,
the third task we address focuses on LiDAR pointclouds. Our initial goal was to
develop a 3D object detector trained on synthetic LiDAR-style pointclouds. While
for images we may expect synth/real-to-real domain shift due to differences in
their appearance (e.g. when source and target images come from different camera
sensors), we did not expect so for LiDAR pointclouds since these active sensors
factor out appearance and provide sampled shapes. However, in practice, we have
seen that it can be domain shift even among real-world LiDAR pointclouds. Factors
such as the sampling parameters of the LiDARs, the sensor suite configuration onboard the ego-vehicle, and the human annotation of 3D bounding boxes, do induce
a domain shift. We show it through comprehensive experiments with different
publicly available datasets and 3D detectors. This redirected our goal towards the
design of a GAN for pointcloud-to-pointcloud translation, a relatively unexplored
topic.
Finally, it is worth to mention that all the synthetic datasets used for these three
tasks, have been designed and generated in the context of this PhD work and will
be publicly released. Overall, we think this PhD presents several steps forward to
encourage leveraging synthetic data for developing deep perception models in the
field of driving assistance and autonomous driving.

Abstract: This manuscript presents a comprehensive survey on recent computer vision based food grain classification techniques. It includes state-of-the-art approaches intended for different grain varieties. The approaches proposed in the literature are analyzed according to the processing stages considered in the classification pipeline, making it easier to identify common techniques and comparisons. Additionally, the type of images considered by each approach (i.e., images from the: visible, infrared, multispectral, hyperspectral bands) together with the strategy used to generate ground truth data (i.e., real and synthetic images) are reviewed. Finally, conclusions highlighting future needs and challenges are presented.

Abstract: Multimodal representations and continual learning are two areas closely related to human intelligence. The former considers the learning of shared representation spaces where information from different modalities can be compared and integrated (we focus on cross-modal retrieval between language and visual representations). The latter studies how to prevent forgetting a previously learned task when learning a new one. While humans excel in these two aspects, deep neural networks are still quite limited. In this paper, we propose a combination of both problems into a continual cross-modal retrieval setting, where we study how the catastrophic interference caused by new tasks impacts the embedding spaces and their cross-modal alignment required for effective retrieval. We propose a general framework that decouples the training, indexing and querying stages. We also identify and study different factors that may lead to forgetting, and propose tools to alleviate it. We found that the indexing stage pays an important role and that simply avoiding reindexing the database with updated embedding networks can lead to significant gains. We evaluated our methods in two image-text retrieval datasets, obtaining significant gains with respect to the fine tuning baseline.

Abstract: Online continual learning aims to learn from a non-IID stream of data from a number of different tasks, where the learner is only allowed to consider data once. Methods are typically allowed to use a limited buffer to store some of the images in the stream. Recently, it was found that feature replay, where an intermediate layer representation of the image is stored (or generated) leads to superior results than image replay, while requiring less memory. Quantized exemplars can further reduce the memory usage. However, a drawback of these methods is that they use a fixed (or very intransigent) backbone network. This significantly limits the learning of representations that can discriminate between all tasks. To address this problem, we propose an auxiliary classifier auto-encoder (ACAE) module for feature replay at intermediate layers with high compression rates. The reduced memory footprint per image allows us to save more exemplars for replay. In our experiments, we conduct task-agnostic evaluation under online continual learning setting and get state-of-the-art performance on ImageNet-Subset, CIFAR100 and CIFAR10 dataset.

Abstract: Neural image compression leverages deep neural networks to outperform traditional image codecs in rate-distortion performance. However, the resulting models are also heavy, computationally demanding and generally optimized for a single rate, limiting their practical use. Focusing on practical image compression, we propose slimmable compressive autoencoders (SlimCAEs), where rate (R) and distortion (D) are jointly optimized for different capacities. Once trained, encoders and decoders can be executed at different capacities, leading to different rates and complexities. We show that a successful implementation of SlimCAEs requires suitable capacity-specific RD tradeoffs. Our experiments show that SlimCAEs are highly flexible models that provide excellent rate-distortion performance, variable rate, and dynamic adjustment of memory, computational cost and latency, thus addressing the main requirements of practical image compression.