arXiv subjects

Josep Lladós

Publications and source records attributed to Josep Lladós.

At least 19 recordsLinked to original sources

arXiv2026

Unapologetically Distributed: A Call for Decentralized Document Analysis

Privacy has become an increasingly important concern in the Document Analysis community, to the extent that in many environments such as archives, governmental institutions, and local businesses, the adoption of automation is restricted by legal and policy constraints. While federated learning has often been regarded as a ``necessary evil'', implying an unavoidable performance trade-off in exchange for decentralization and privacy, many prior works overlook its potential to improve robustness to out-of-distribution data. In this paper, we present Unapologetically Distributed, the first comprehensive study evaluating distributed learning in Document Analysis along three key axes simultaneously: the tasks addressed, the architectures employed, and the fine-tuning strategies applied. Specifically, we demonstrate how various distributed training approaches enhance generalization capabilities across diverse tasks such as Table Recognition, handwriting recognition, and Word Spotting, particularly during transfer learning stages. Our results provide strong evidence that decentralization is not merely a constraint, but a valuable opportunity to improve model robustness and adaptability in real-world Document Analysis scenarios.

cs.CV↗

arXiv2026

Robust Interpretation of Historical Documents in Knowledge Graphs Through Query Inference and Execution

The emergence of Large Language Models (LLMs) has redefined how users interact with information in digital environments. However, their widespread and often indiscriminate integration has raised significant concerns regarding reliability and trustworthiness issues that are particularly critical when accessing digital libraries and historical archives. How can one leverage the generalization capacity of an LLM without losing the level of accountability required for an archival institution? In this paper, we present an agentic retrieval system designed to deliver more accurate and verifiable access to historical data while preserving much of the flexibility associated with unconstrained LLMs. As a contribution to historical document analysis, we compare traditional Retrieval-Augmented Generation (RAG) with an agentic GraphRAG architecture in their ability to deliver historical information under realistic conditions, including the presence of OCR and transcription errors. We introduce a semi-symbolic framework that integrates word-spotting techniques for post-OCR correction with a knowledge graph representation that enables the agent to access information through synthesized queries. The interleaved collaboration between word spotting and code generation allows the agent to construct strong retrieval queries that are robust to misinterpretation and hallucination, while still leveraging approximate search when noise and uncertainty, common in historical document analysis, would otherwise hinder precise retrieval.

cs.IR↗

arXiv2026

Conversational Retrieval and On-the-Fly Knowledge Modeling of Historical Penitentiary Repression Records

Recent developments in digital libraries increasingly favor conversational and natural language access to information through Retrieval-Augmented Generation (RAG). Although these approaches are effective for extractive tasks grounded in individual records, they remain limited in their ability to interpret document collections holistically and to incorporate expert knowledge dynamically. In this article, we present a document analysis system designed for the management of historical digital libraries that supports on-the-fly knowledge modeling. The system is equipped with the capability to store facts produced either by expert archivists or derived from document retrieval processes within a graph-based structure. Through continuous professional interaction, the system can retrieve information not only from primary sources such as documents, but also from previously modeled knowledge, with the graph-based index acting as a memory for the language model to access. This enables increasingly complex queries involving long-term dependencies across documents, link discovery, and the integration of expert knowledge that may not be explicitly present in the original sources. As a result, the proposed approach facilitates the generation of richer and more comprehensive information.

cs.IR↗

arXiv2026

CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models

Preserving facial identity under extreme stylistic transformation remains a major challenge in generative art. In graffiti, a high-contrast, abstract medium, subtle distortions to the eyes, nose, or mouth can erase the subject's recognizability, undermining both personal and cultural authenticity. We present CraftGraffiti, an end-to-end text-guided graffiti generation framework designed with facial feature preservation as a primary objective. Given an input image and a style and pose descriptive prompt, CraftGraffiti first applies graffiti style transfer via LoRA-fine-tuned pretrained diffusion transformer, then enforces identity fidelity through a face-consistent self-attention mechanism that augments attention layers with explicit identity embeddings. Pose customization is achieved without keypoints, using CLIP-guided prompt extension to enable dynamic re-posing while retaining facial coherence. We formally justify and empirically validate the "style-first, identity-after" paradigm, showing it reduces attribute drift compared to the reverse order. Quantitative results demonstrate competitive facial feature consistency and state-of-the-art aesthetic and human preference scores, while qualitative analyses and a live deployment at the Cruilla Festival highlight the system's real-world creative impact. CraftGraffiti advances the goal of identity-respectful AI-assisted artistry, offering a principled approach for blending stylistic freedom with recognizability in creative AI applications.

cs.CV↗

arXiv2026

Visual Model Checking: Graph-Based Inference of Visual Routines for Image Retrieval

Information retrieval lies at the foundation of the modern digital industry. While natural language search has seen dramatic progress in recent years largely driven by embedding-based models and large-scale pretraining, the field still faces significant challenges. Specifically, queries that involve complex relationships, object compositions, or precise constraints such as identities, counts and proportions often remain unresolved or unreliable within current frameworks. In this paper, we propose a novel framework that integrates formal verification into deep learning-based image retrieval through a synergistic combination of graph-based verification methods and neural code generation. Our approach aims to support open-vocabulary natural language queries while producing results that are both trustworthy and verifiable. By grounding retrieval results in a system of formal reasoning, we move beyond the ambiguity and approximation that often characterize vector representations. Instead of accepting uncertainty as a given, our framework explicitly verifies each atomic truth in the user query against the retrieved content. This allows us to not only return matching results, but also to identify and mark which specific constraints are satisfied and which remain unmet, thereby offering a more transparent and accountable retrieval process while boosting the results of the most popular embedding-based approaches.

cs.AI↗

arXiv2025

GAN-based Content-Conditioned Generation of Handwritten Musical Symbols

The field of Optical Music Recognition (OMR) is currently hindered by the scarcity of real annotated data, particularly when dealing with handwritten historical musical scores. In similar fields, such as Handwritten Text Recognition, it was proven that synthetic examples produced with image generation techniques could help to train better-performing recognition architectures. This study explores the generation of realistic, handwritten-looking scores by implementing a music symbol-level Generative Adversarial Network (GAN) and assembling its output into a full score using the Smashcima engraving software. We have systematically evaluated the visual fidelity of these generated samples, concluding that the generated symbols exhibit a high degree of realism, marking significant progress in synthetic score generation.

cs.CV↗

arXiv2025

The OCR Quest for Generalization: Learning to recognize low-resource alphabets with model editing

Achieving robustness in recognition systems across diverse domains is crucial for their practical utility. While ample data availability is usually assumed, low-resource languages, such as ancient manuscripts and non-western languages, tend to be kept out of the equations of massive pretraining and foundational techniques due to an under representation. In this work, we aim for building models which can generalize to new distributions of data, such as alphabets, faster than centralized fine-tune strategies. For doing so, we take advantage of the recent advancements in model editing to enhance the incorporation of unseen scripts (low-resource learning). In contrast to state-of-the-art meta-learning, we showcase the effectiveness of domain merging in sparse distributions of data, with agnosticity of its relation to the overall distribution or any other prototyping necessity. Even when using the same exact training data, our experiments showcase significant performance boosts in \textbf{transfer learning} to new alphabets and \textbf{out-of-domain evaluation} in challenging domain shifts, including historical ciphered texts and non-Latin scripts. This research contributes a novel approach into building models that can easily adopt under-represented alphabets and, therefore, enable document recognition to a wider set of contexts and cultures.

cs.LG↗

arXiv2025

DistilDoc: Knowledge Distillation for Visually-Rich Document Applications

This work explores knowledge distillation (KD) for visually-rich document (VRD) applications such as document layout analysis (DLA) and document image classification (DIC). While VRD research is dependent on increasingly sophisticated and cumbersome models, the field has neglected to study efficiency via model compression. Here, we design a KD experimentation methodology for more lean, performant models on document understanding (DU) tasks that are integral within larger task pipelines. We carefully selected KD strategies (response-based, feature-based) for distilling knowledge to and from backbones with different architectures (ResNet, ViT, DiT) and capacities (base, small, tiny). We study what affects the teacher-student knowledge gap and find that some methods (tuned vanilla KD, MSE, SimKD with an apt projector) can consistently outperform supervised student training. Furthermore, we design downstream task setups to evaluate covariate shift and the robustness of distilled DLA models on zero-shot layout-aware document visual question answering (DocVQA). DLA-KD experiments result in a large mAP knowledge gap, which unpredictably translates to downstream robustness, accentuating the need to further explore how to efficiently obtain more semantic document layout awareness.

cs.CV↗

arXiv2025

FastTextSpotter: A High-Efficiency Transformer for Multilingual Scene Text Spotting

The proliferation of scene text in both structured and unstructured environments presents significant challenges in optical character recognition (OCR), necessitating more efficient and robust text spotting solutions. This paper presents FastTextSpotter, a framework that integrates a Swin Transformer visual backbone with a Transformer Encoder-Decoder architecture, enhanced by a novel, faster self-attention unit, SAC2, to improve processing speeds while maintaining accuracy. FastTextSpotter has been validated across multiple datasets, including ICDAR2015 for regular texts and CTW1500 and TotalText for arbitrary-shaped texts, benchmarking against current state-of-the-art models. Our results indicate that FastTextSpotter not only achieves superior accuracy in detecting and recognizing multilingual scene text (English and Vietnamese) but also improves model efficiency, thereby setting new benchmarks in the field. This study underscores the potential of advanced transformer architectures in improving the adaptability and speed of text spotting applications in diverse real-world settings. The dataset, code, and pre-trained models have been released in our Github.

cs.CV↗

arXiv2024

FASTER: A Font-Agnostic Scene Text Editing and Rendering Framework

Scene Text Editing (STE) is a challenging research problem, that primarily aims towards modifying existing texts in an image while preserving the background and the font style of the original text. Despite its utility in numerous real-world applications, existing style-transfer-based approaches have shown sub-par editing performance due to (1) complex image backgrounds, (2) diverse font attributes, and (3) varying word lengths within the text. To address such limitations, in this paper, we propose a novel font-agnostic scene text editing and rendering framework, named FASTER, for simultaneously generating text in arbitrary styles and locations while preserving a natural and realistic appearance and structure. A combined fusion of target mask generation and style transfer units, with a cascaded self-attention mechanism has been proposed to focus on multi-level text region edits to handle varying word lengths. Extensive evaluation on a real-world database with further subjective human evaluation study indicates the superiority of FASTER in both scene text editing and rendering tasks, in terms of model performance and efficiency. Our code will be released upon acceptance.

cs.CV↗

arXiv2024

GlobalDoc: A Cross-Modal Vision-Language Framework for Real-World Document Image Retrieval and Classification

Visual document understanding (VDU) has rapidly advanced with the development of powerful multi-modal language models. However, these models typically require extensive document pre-training data to learn intermediate representations and often suffer a significant performance drop in real-world online industrial settings. A primary issue is their heavy reliance on OCR engines to extract local positional information within document pages, which limits the models' ability to capture global information and hinders their generalizability, flexibility, and robustness. In this paper, we introduce GlobalDoc, a cross-modal transformer-based architecture pre-trained in a self-supervised manner using three novel pretext objective tasks. GlobalDoc improves the learning of richer semantic concepts by unifying language and visual representations, resulting in more transferable models. For proper evaluation, we also propose two novel document-level downstream VDU tasks, Few-Shot Document Image Classification (DIC) and Content-based Document Image Retrieval (DIR), designed to simulate industrial scenarios more closely. Extensive experimentation has been conducted to demonstrate GlobalDoc's effectiveness in practical settings.

cs.CV↗

arXiv2024

Towards Generative Class Prompt Learning for Fine-grained Visual Recognition

Although foundational vision-language models (VLMs) have proven to be very successful for various semantic discrimination tasks, they still struggle to perform faithfully for fine-grained categorization. Moreover, foundational models trained on one domain do not generalize well on a different domain without fine-tuning. We attribute these to the limitations of the VLM's semantic representations and attempt to improve their fine-grained visual awareness using generative modeling. Specifically, we propose two novel methods: Generative Class Prompt Learning (GCPL) and Contrastive Multi-class Prompt Learning (CoMPLe). Utilizing text-to-image diffusion models, GCPL significantly improves the visio-linguistic synergy in class embeddings by conditioning on few-shot exemplars with learnable class prompts. CoMPLe builds on this foundation by introducing a contrastive learning component that encourages inter-class separation during the generative optimization process. Our empirical results demonstrate that such a generative class prompt learning approach substantially outperform existing methods, offering a better alternative to few shot image recognition challenges. The source code will be made available at: https://github.com/soumitri2001/GCPL.

cs.CV↗

arXiv2024

Fetch-A-Set: A Large-Scale OCR-Free Benchmark for Historical Document Retrieval

This paper introduces Fetch-A-Set (FAS), a comprehensive benchmark tailored for legislative historical document analysis systems, addressing the challenges of large-scale document retrieval in historical contexts. The benchmark comprises a vast repository of documents dating back to the XVII century, serving both as a training resource and an evaluation benchmark for retrieval systems. It fills a critical gap in the literature by focusing on complex extractive tasks within the domain of cultural heritage. The proposed benchmark tackles the multifaceted problem of historical document analysis, including text-to-image retrieval for queries and image-to-text topic extraction from document fragments, all while accommodating varying levels of document legibility. This benchmark aims to spur advancements in the field by providing baselines and data for the development and evaluation of robust historical document retrieval systems, particularly in scenarios characterized by wide historical spectrum.

cs.IR↗

arXiv2024

DocSynthv2: A Practical Autoregressive Modeling for Document Generation

While the generation of document layouts has been extensively explored, comprehensive document generation encompassing both layout and content presents a more complex challenge. This paper delves into this advanced domain, proposing a novel approach called DocSynthv2 through the development of a simple yet effective autoregressive structured model. Our model, distinct in its integration of both layout and textual cues, marks a step beyond existing layout-generation approaches. By focusing on the relationship between the structural elements and the textual content within documents, we aim to generate cohesive and contextually relevant documents without any reliance on visual components. Through experimental studies on our curated benchmark for the new task, we demonstrate the ability of our model combining layout and textual information in enhancing the generation quality and relevance of documents, opening new pathways for research in document creation and automated design. Our findings emphasize the effectiveness of autoregressive models in handling complex document generation tasks.

cs.CV↗

arXiv2024

LayeredDoc: Domain Adaptive Document Restoration with a Layer Separation Approach

The rapid evolution of intelligent document processing systems demands robust solutions that adapt to diverse domains without extensive retraining. Traditional methods often falter with variable document types, leading to poor performance. To overcome these limitations, this paper introduces a text-graphic layer separation approach that enhances domain adaptability in document image restoration (DIR) systems. We propose LayeredDoc, which utilizes two layers of information: the first targets coarse-grained graphic components, while the second refines machine-printed textual content. This hierarchical DIR framework dynamically adjusts to the characteristics of the input document, facilitating effective domain adaptation. We evaluated our approach both qualitatively and quantitatively using a new real-world dataset, LayeredDocDB, developed for this study. Initially trained on a synthetically generated dataset, our model demonstrates strong generalization capabilities for the DIR task, offering a promising solution for handling variability in real-world data. Our code is accessible on GitHub.

cs.CV↗

arXiv2024

SketchGPT: Autoregressive Modeling for Sketch Generation and Recognition

We present SketchGPT, a flexible framework that employs a sequence-to-sequence autoregressive model for sketch generation, and completion, and an interpretation case study for sketch recognition. By mapping complex sketches into simplified sequences of abstract primitives, our approach significantly streamlines the input for autoregressive modeling. SketchGPT leverages the next token prediction objective strategy to understand sketch patterns, facilitating the creation and completion of drawings and also categorizing them accurately. This proposed sketch representation strategy aids in overcoming existing challenges of autoregressive modeling for continuous stroke data, enabling smoother model training and competitive performance. Our findings exhibit SketchGPT's capability to generate a diverse variety of drawings by adding both qualitative and quantitative comparisons with existing state-of-the-art, along with a comprehensive human evaluation study. The code and pretrained models will be released on our official GitHub.

cs.CV↗

arXiv2024

GeoContrastNet: Contrastive Key-Value Edge Learning for Language-Agnostic Document Understanding

This paper presents GeoContrastNet, a language-agnostic framework to structured document understanding (DU) by integrating a contrastive learning objective with graph attention networks (GATs), emphasizing the significant role of geometric features. We propose a novel methodology that combines geometric edge features with visual features within an overall two-staged GAT-based framework, demonstrating promising results in both link prediction and semantic entity recognition performance. Our findings reveal that combining both geometric and visual features could match the capabilities of large DU models that rely heavily on Optical Character Recognition (OCR) features in terms of performance accuracy and efficiency. This approach underscores the critical importance of relational layout information between the named text entities in a semi-structured layout of a page. Specifically, our results highlight the model's proficiency in identifying key-value relationships within the FUNSD dataset for forms and also discovering the spatial relationships in table-structured layouts for RVLCDIP business invoices. Our code and pretrained models will be accessible on our official GitHub.

cs.CV↗

arXiv2024

GraphKD: Exploring Knowledge Distillation Towards Document Object Detection with Structured Graph Creation

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: https://github.com/ayanban011/GraphKD.

cs.CV↗