Ruben Tito, Khanh Nguyen, Marlon Tobaben, Raouf Kerkouche, Mohamed Ali Souibgui, Kangsoo Jung, et al. (2023). Privacy-Aware Document Visual Question Answering.
Abstract: Document Visual Question Answering (DocVQA) is a fast growing branch of document understanding. Despite the fact that documents contain sensitive or copyrighted information, none of the current DocVQA methods offers strong privacy guarantees.
In this work, we explore privacy in the domain of DocVQA for the first time. We highlight privacy issues in state of the art multi-modal LLM models used for DocVQA, and explore possible solutions.
Specifically, we focus on the invoice processing use case as a realistic, widely used scenario for document understanding, and propose a large scale DocVQA dataset comprising invoice documents and associated questions and answers. We employ a federated learning scheme, that reflects the real-life distribution of documents in different businesses, and we explore the use case where the ID of the invoice issuer is the sensitive information to be protected.
We demonstrate that non-private models tend to memorise, behaviour that can lead to exposing private information. We then evaluate baseline training schemes employing federated learning and differential privacy in this multi-modal scenario, where the sensitive information might be exposed through any of the two input modalities: vision (document image) or language (OCR tokens).
Finally, we design an attack exploiting the memorisation effect of the model, and demonstrate its effectiveness in probing different DocVQA models.
|
Daniel Marczak, Sebastian Cygert, Tomasz Trzcinski, & Bartlomiej Twardowski. (2023). Revisiting Supervision for Continual Representation Learning.
Abstract: In the field of continual learning, models are designed to learn tasks one after the other. While most research has centered on supervised continual learning, recent studies have highlighted the strengths of self-supervised continual representation learning. The improved transferability of representations built with self-supervised methods is often associated with the role played by the multi-layer perceptron projector. In this work, we depart from this observation and reexamine the role of supervision in continual representation learning. We reckon that additional information, such as human annotations, should not deteriorate the quality of representations. Our findings show that supervised models when enhanced with a multi-layer perceptron head, can outperform self-supervised models in continual representation learning.
|
Jose Luis Gomez, Manuel Silva, Antonio Seoane, Agnes Borras, Mario Noriega, German Ros, et al. (2023). All for One, and One for All: UrbanSyn Dataset, the third Musketeer of Synthetic Driving Scenes.
Abstract: We introduce UrbanSyn, a photorealistic dataset acquired through semi-procedurally generated synthetic urban driving scenarios. Developed using high-quality geometry and materials, UrbanSyn provides pixel-level ground truth, including depth, semantic segmentation, and instance segmentation with object bounding boxes and occlusion degree. It complements GTAV and Synscapes datasets to form what we coin as the 'Three Musketeers'. We demonstrate the value of the Three Musketeers in unsupervised domain adaptation for image semantic segmentation. Results on real-world datasets, Cityscapes, Mapillary Vistas, and BDD100K, establish new benchmarks, largely attributed to UrbanSyn. We make UrbanSyn openly and freely accessible (this http URL).
|
Razieh Rastgoo, Kourosh Kiani, & Sergio Escalera. (2024). A transformer model for boundary detection in continuous sign language. MTAP - Multimedia Tools and Applications, .
Abstract: Sign Language Recognition (SLR) has garnered significant attention from researchers in recent years, particularly the intricate domain of Continuous Sign Language Recognition (CSLR), which presents heightened complexity compared to Isolated Sign Language Recognition (ISLR). One of the prominent challenges in CSLR pertains to accurately detecting the boundaries of isolated signs within a continuous video stream. Additionally, the reliance on handcrafted features in existing models poses a challenge to achieving optimal accuracy. To surmount these challenges, we propose a novel approach utilizing a Transformer-based model. Unlike traditional models, our approach focuses on enhancing accuracy while eliminating the need for handcrafted features. The Transformer model is employed for both ISLR and CSLR. The training process involves using isolated sign videos, where hand keypoint features extracted from the input video are enriched using the Transformer model. Subsequently, these enriched features are forwarded to the final classification layer. The trained model, coupled with a post-processing method, is then applied to detect isolated sign boundaries within continuous sign videos. The evaluation of our model is conducted on two distinct datasets, including both continuous signs and their corresponding isolated signs, demonstrates promising results.
|
Vacit Oguz Yazici, Longlong Yu, Arnau Ramisa, Luis Herranz, & Joost Van de Weijer. (2024). Main product detection with graph networks for fashion. MTAP - Multimedia Tools and Applications, 83, 3215–3231.
Abstract: Computer vision has established a foothold in the online fashion retail industry. Main product detection is a crucial step of vision-based fashion product feed parsing pipelines, focused on identifying the bounding boxes that contain the product being sold in the gallery of images of the product page. The current state-of-the-art approach does not leverage the relations between regions in the image, and treats images of the same product independently, therefore not fully exploiting visual and product contextual information. In this paper, we propose a model that incorporates Graph Convolutional Networks (GCN) that jointly represent all detected bounding boxes in the gallery as nodes. We show that the proposed method is better than the state-of-the-art, especially, when we consider the scenario where title-input is missing at inference time and for cross-dataset evaluation, our method outperforms previous approaches by a large margin.
|
Javier Vazquez, Graham D. Finlayson, & Luis Herranz. (2024). Improving the perception of low-light enhanced images. Optics Express, 32(4), 5174–5190.
Abstract: Improving images captured under low-light conditions has become an important topic in computational color imaging, as it has a wide range of applications. Most current methods are either based on handcrafted features or on end-to-end training of deep neural networks that mostly focus on minimizing some distortion metric —such as PSNR or SSIM— on a set of training images. However, the minimization of distortion metrics does not mean that the results are optimal in terms of perception (i.e. perceptual quality). As an example, the perception-distortion trade-off states that, close to the optimal results, improving distortion results in worsening perception. This means that current low-light image enhancement methods —that focus on distortion minimization— cannot be optimal in the sense of obtaining a good image in terms of perception errors. In this paper, we propose a post-processing approach in which, given the original low-light image and the result of a specific method, we are able to obtain a result that resembles as much as possible that of the original method, but, at the same time, giving an improvement in the perception of the final image. More in detail, our method follows the hypothesis that in order to minimally modify the perception of an input image, any modification should be a combination of a local change in the shading across a scene and a global change in illumination color. We demonstrate the ability of our method quantitatively using perceptual blind image metrics such as BRISQUE, NIQE, or UNIQUE, and through user preference tests.
|
Beata Megyesi, Alicia Fornes, Nils Kopal, & Benedek Lang. (2024). Historical Cryptology. In Learning and Experiencing Cryptography with CrypTool and SageMath.
Abstract: Historical cryptology studies (original) encrypted manuscripts, often handwritten sources, produced in our history. These historical sources can be found in archives, often hidden without any indexing and therefore hard to locate. Once found they need to be digitized and turned into a machine-readable text format before they can be deciphered with computational methods. The focus of historical cryptology is not primarily the development of sophisticated algorithms for decipherment, but rather the entire process of analysis of the encrypted source from collection and digitization to transcription and decryption. The process also includes the interpretation and contextualization of the message set in its historical context. There are many challenges on the way, such as mistakes made by the scribe, errors made by the transcriber, damaged pages, handwriting styles that are difficult to interpret, historical languages from various time periods, and hidden underlying language of the message. Ciphertexts vary greatly in terms of their code system and symbol sets used with more or less distinguishable symbols. Ciphertexts can be embedded in clearly written text, or shorter or longer sequences of cleartext can be embedded in the ciphertext. The ciphers used mostly in historical times are substitutions (simple, homophonic, or polyphonic), with or without nomenclatures, encoded as digits or symbol sequences, with or without spaces. So the circumstances are different from those in modern cryptography which focuses on methods (algorithms) and their strengths and assumes that the algorithm is applied correctly. For both historical and modern cryptology, attack vectors outside the algorithm are applied like implementation flaws and side-channel attacks. In this chapter, we give an introduction to the field of historical cryptology and present an overview of how researchers today process historical encrypted sources.
|
Mustafa Hajij, Mathilde Papillon, Florian Frantzen, Jens Agerberg, Ibrahem AlJabea, Ruben Ballester, et al. (2024). TopoX: A Suite of Python Packages for Machine Learning on Topological Domains.
Abstract: We introduce TopoX, a Python software suite that provides reliable and user-friendly building blocks for computing and machine learning on topological domains that extend graphs: hypergraphs, simplicial, cellular, path and combinatorial complexes. TopoX consists of three packages: TopoNetX facilitates constructing and computing on these domains, including working with nodes, edges and higher-order cells; TopoEmbedX provides methods to embed topological domains into vector spaces, akin to popular graph-based embedding algorithms such as node2vec; TopoModelx is built on top of PyTorch and offers a comprehensive toolbox of higher-order message passing functions for neural networks on topological domains. The extensively documented and unit-tested source code of TopoX is available under MIT license at this https URL.
|
German Barquero, Sergio Escalera, & Cristina Palmero. (2024). Seamless Human Motion Composition with Blended Positional Encodings.
Abstract: Conditional human motion generation is an important topic with many applications in virtual reality, gaming, and robotics. While prior works have focused on generating motion guided by text, music, or scenes, these typically result in isolated motions confined to short durations. Instead, we address the generation of long, continuous sequences guided by a series of varying textual descriptions. In this context, we introduce FlowMDM, the first diffusion-based model that generates seamless Human Motion Compositions (HMC) without any postprocessing or redundant denoising steps. For this, we introduce the Blended Positional Encodings, a technique that leverages both absolute and relative positional encodings in the denoising chain. More specifically, global motion coherence is recovered at the absolute stage, whereas smooth and realistic transitions are built at the relative stage. As a result, we achieve state-of-the-art results in terms of accuracy, realism, and smoothness on the Babel and HumanML3D datasets. FlowMDM excels when trained with only a single description per motion sequence thanks to its Pose-Centric Cross-ATtention, which makes it robust against varying text descriptions at inference time. Finally, to address the limitations of existing HMC metrics, we propose two new metrics: the Peak Jerk and the Area Under the Jerk, to detect abrupt transitions.
|
Ayan Banerjee, Sanket Biswas, Josep Llados, & Umapada Pal. (2024). GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation.
Abstract: Object detection in documents is a key step to automate the structural elements identification process in a digital or scanned document through understanding the hierarchical structure and relationships between different elements. Large and complex models, while achieving high accuracy, can be computationally expensive and memory-intensive, making them impractical for deployment on resource constrained devices. Knowledge distillation allows us to create small and more efficient models that retain much of the performance of their larger counterparts. Here we present a graph-based knowledge distillation framework to correctly identify and localize the document objects in a document image. Here, we design a structured graph with nodes containing proposal-level features and edges representing the relationship between the different proposal regions. Also, to reduce text bias an adaptive node sampling strategy is designed to prune the weight distribution and put more weightage on non-text nodes. We encode the complete graph as a knowledge representation and transfer it from the teacher to the student through the proposed distillation loss by effectively capturing both local and global information concurrently. Extensive experimentation on competitive benchmarks demonstrates that the proposed framework outperforms the current state-of-the-art approaches. The code will be available at: this https URL.
|
Tao Wu, Kai Wang, Chuanming Tang, & Jianlin Zhang. (2024). Diffusion-based network for unsupervised landmark detection. Knowledge-Based Systems, 292, 111627.
Abstract: Landmark detection is a fundamental task aiming at identifying specific landmarks that serve as representations of distinct object features within an image. However, the present landmark detection algorithms often adopt complex architectures and are trained in a supervised manner using large datasets to achieve satisfactory performance. When faced with limited data, these algorithms tend to experience a notable decline in accuracy. To address these drawbacks, we propose a novel diffusion-based network (DBN) for unsupervised landmark detection, which leverages the generation ability of the diffusion models to detect the landmark locations. In particular, we introduce a dual-branch encoder (DualE) for extracting visual features and predicting landmarks. Additionally, we lighten the decoder structure for faster inference, referred to as LightD. By this means, we avoid relying on extensive data comparison and the necessity of designing complex architectures as in previous methods. Experiments on CelebA, AFLW, 300W and Deepfashion benchmarks have shown that DBN performs state-of-the-art compared to the existing methods. Furthermore, DBN shows robustness even when faced with limited data cases.
|
Jaume Amores. (2013). Multiple Instance Classification: review, taxonomy and comparative study. AI - Artificial Intelligence, 201, 81–105.
Abstract: Multiple Instance Learning (MIL) has become an important topic in the pattern recognition community, and many solutions to this problemhave been proposed until now. Despite this fact, there is a lack of comparative studies that shed light into the characteristics and behavior of the different methods. In this work we provide such an analysis focused on the classification task (i.e.,leaving out other learning tasks such as regression). In order to perform our study, we implemented
fourteen methods grouped into three different families. We analyze the performance of the approaches across a variety of well-known databases, and we also study their behavior in synthetic scenarios in order to highlight their characteristics. As a result of this analysis, we conclude that methods that extract global bag-level information show a clearly superior performance in general. In this sense, the analysis permits us to understand why some types of methods are more successful than others, and it permits us to establish guidelines in the design of new MIL
methods.
Keywords: Multi-instance learning; Codebook; Bag-of-Words
|
Juan Ramon Terven Salinas, Joaquin Salas, & Bogdan Raducanu. (2014). New Opportunities for Computer Vision-Based Assistive Technology Systems for the Visually Impaired. COMP - Computer, 47(4), 52–58.
Abstract: Computing advances and increased smartphone use gives technology system designers greater flexibility in exploiting computer vision to support visually impaired users. Understanding these users' needs will certainly provide insight for the development of improved usability of computing devices.
|
Marina Alberti, Simone Balocco, Carlo Gatta, Francesco Ciompi, Oriol Pujol, Joana Silva, et al. (2012). Automatic Bifurcation Detection in Coronary IVUS Sequences. TBME - IEEE Transactions on Biomedical Engineering, 59(4), 1022–2031.
Abstract: In this paper, we present a fully automatic method which identifies every bifurcation in an intravascular ultrasound (IVUS) sequence, the corresponding frames, the angular orientation with respect to the IVUS acquisition, and the extension. This goal is reached using a two-level classification scheme: first, a classifier is applied to a set of textural features extracted from each image of a sequence. A comparison among three state-of-the-art discriminative classifiers (AdaBoost, random forest, and support vector machine) is performed to identify the most suitable method for the branching detection task. Second, the results are improved by exploiting contextual information using a multiscale stacked sequential learning scheme. The results are then successively refined using a-priori information about branching dimensions and geometry. The proposed approach provides a robust tool for the quick review of pullback sequences, facilitating the evaluation of the lesion at bifurcation sites. The proposed method reaches an F-Measure score of 86.35%, while the F-Measure scores for inter- and intraobserver variability are 71.63% and 76.18%, respectively. The obtained results are positive. Especially, considering the branching detection task is very challenging, due to high variability in bifurcation dimensions and appearance.
|
David Geronimo, Joan Serrat, Antonio Lopez, & Ramon Baldrich. (2013). Traffic sign recognition for computer vision project-based learning. T-EDUC - IEEE Transactions on Education, 56(3), 364–371.
Abstract: This paper presents a graduate course project on computer vision. The aim of the project is to detect and recognize traffic signs in video sequences recorded by an on-board vehicle camera. This is a demanding problem, given that traffic sign recognition is one of the most challenging problems for driving assistance systems. Equally, it is motivating for the students given that it is a real-life problem. Furthermore, it gives them the opportunity to appreciate the difficulty of real-world vision problems and to assess the extent to which this problem can be solved by modern computer vision and pattern classification techniques taught in the classroom. The learning objectives of the course are introduced, as are the constraints imposed on its design, such as the diversity of students' background and the amount of time they and their instructors dedicate to the course. The paper also describes the course contents, schedule, and how the project-based learning approach is applied. The outcomes of the course are discussed, including both the students' marks and their personal feedback.
Keywords: traffic signs
|
