From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents

• URL: http://arxiv.org/abs/2506.20326v1
• Date: Wed, 25 Jun 2025 11:14:04 GMT
• Title: From Codicology to Code: A Comparative Study of Transformer and YOLO-based Detectors for Layout Analysis in Historical Documents
• Abstract summary: This paper benchmarks five state-of-the-art object detection architectures on three annotated datasets.<n>We evaluate two Transformer-based models (Co-DETR, Grounding DINO) against three YOLO variants.<n>We conclude that a key trade-off exists between the global context awareness of Transformers, ideal for structured layouts, and the superior generalization of CNN-OBB models for visually diverse and complex documents.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Robust Document Layout Analysis (DLA) is critical for the automated processing and understanding of historical documents with complex page organizations. This paper benchmarks five state-of-the-art object detection architectures on three annotated datasets representing a spectrum of codicological complexity: The e-NDP, a corpus of Parisian medieval registers (1326-1504); CATMuS, a diverse multiclass dataset derived from various medieval and modern sources (ca.12th-17th centuries) and HORAE, a corpus of decorated books of hours (ca.13th-16th centuries). We evaluate two Transformer-based models (Co-DETR, Grounding DINO) against three YOLO variants (AABB, OBB, and YOLO-World). Our findings reveal significant performance variations dependent on model architecture, data set characteristics, and bounding box representation. In the e-NDP dataset, Co-DETR achieves state-of-the-art results (0.752 mAP@.50:.95), closely followed by YOLOv11X-OBB (0.721). Conversely, on the more complex CATMuS and HORAE datasets, the CNN-based YOLOv11x-OBB significantly outperforms all other models (0.564 and 0.568, respectively). This study unequivocally demonstrates that using Oriented Bounding Boxes (OBB) is not a minor refinement but a fundamental requirement for accurately modeling the non-Cartesian nature of historical manuscripts. We conclude that a key trade-off exists between the global context awareness of Transformers, ideal for structured layouts, and the superior generalization of CNN-OBB models for visually diverse and complex documents.

Related papers

• Architecture-Dependent Causal Transfer of Activation States Across Large Language Models [51.56484100374058]
  Internal language activation states can be transferred causally between different large language models.<n>Injecting projected activations into a target model during generation produces a statistically significant, preregistered causal effect.<n>We conclude that end-to-end activation-state transfer between LLMs, as currently implemented, is architecture-dependent rather than universal.
  arXiv  Detail & Related papers  (2026-08-17T09:53:27Z)
• Beyond Scale and Generation: Understanding Language Model-based Entity Matching [18.904187328683513]
  We show that model variant is critical for bi-encoders.<n>Generative matchers do not universally outperform cross-encoders.<n> larger models rely more heavily on shortcut learning.
  arXiv  Detail & Related papers  (2026-07-27T17:29:18Z)
• PereStruct: Multimodal Semantic Assembly for Robust Historical Document Parsing [35.18016233072556]
  We develop an automated pipeline designed for parsing historical newspapers.<n>Our approach combines a fine-tuned YOLO architecture for layout analysis and block detection, trained on 1,426 fully human-annotated scanned pages.<n>This multi-modal integration yields state-of-the-art performance, achieving an F1 score of 0.904 on block-to-article mapping.
  arXiv  Detail & Related papers  (2026-06-03T13:10:47Z)
• MinerU2.5-Pro: Pushing the Limits of Data-Centric Document Parsing at Scale [92.09717763663873]
  We present MinerU2.5-Pro, which advances the state of the art purely through data engineering and training strategy design.<n>At its core is a Data Engine co-designed around coverage, informativeness, and annotation accuracy.<n>We show that MinerU2.5-Pro achieves 95.69 on OmniDocBench v1.6, improving over the same-architecture baseline by 2.71 points and surpassing all existing methods.
  arXiv  Detail & Related papers  (2026-04-06T15:44:18Z)
• PerSoMed: A Large-Scale Balanced Dataset for Persian Social Media Text Classification [0.052017164170440056]
  This research introduces the first large-scale, well-balanced Persian social media text classification dataset.<n>The dataset comprises 36,000 posts across nine categories (Economic, Artistic, Sports, Political, Social, Health, Psychological, Historical, and Science & Technology)
  arXiv  Detail & Related papers  (2026-02-22T20:53:08Z)
• S3OD: Towards Generalizable Salient Object Detection with Synthetic Data [38.10559747985342]
  We introduce S3OD, a dataset of over 139,000 high-resolution images created through our multi-modal diffusion pipeline.<n>We propose a streamlined multi-mask decoder that naturally handles the inherent ambiguity in salient object detection.
  arXiv  Detail & Related papers  (2025-10-24T16:10:09Z)
• U-Bench: A Comprehensive Understanding of U-Net through 100-Variant Benchmarking [13.41099918346476]
  U-Net has been the dominant architecture in medical image segmentation, leading to the development of thousands of U-shaped variants.<n>Despite its widespread adoption, there is still no comprehensive benchmark to systematically evaluate their performance and utility.<n>We present U-Bench, the first large-scale, statistically rigorous benchmark that evaluates 100 U-Net variants across 28 datasets and 10 imaging modalities.
  arXiv  Detail & Related papers  (2025-10-08T14:06:17Z)
• SitEmb-v1.5: Improved Context-Aware Dense Retrieval for Semantic Association and Long Story Comprehension [77.93156509994994]
  We show how to represent short chunks in a way that is conditioned on a broader context window to enhance retrieval performance.<n>Existing embedding models are not well-equipped to encode such situated context effectively.<n>Our method substantially outperforms state-of-the-art embedding models.
  arXiv  Detail & Related papers  (2025-08-03T23:59:31Z)
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception [58.06752127687312]
  We propose YOLOv13, an accurate and lightweight object detector.<n>We propose a Hypergraph-based Adaptive Correlation Enhancement (HyperACE) mechanism.<n>We also propose a Full-Pipeline Aggregation-and-Distribution (FullPAD) paradigm.
  arXiv  Detail & Related papers  (2025-06-21T15:15:03Z)
• MonkeyOCR: Document Parsing with a Structure-Recognition-Relation Triplet Paradigm [60.14048367611333]
  MonkeyOCR is a vision-language model for document parsing.<n>It advances the state of the art by leveraging a Structure-Recognition-Relation (SRR) triplet paradigm.
  arXiv  Detail & Related papers  (2025-06-05T16:34:57Z)
• Token and Span Classification for Entity Recognition in French Historical Encyclopedias [0.0]
  Named Entity Recognition (NER) in historical texts presents unique challenges due to non-standardized language, archaic orthography, and nested or overlapping entities.<n>This study benchmarks a diverse set of NER approaches, ranging from classical Conditional Random Fields (CRFs) and spaCy-based models to transformer-based architectures.<n>Experiments are conducted on the GeoEDdA dataset, a richly annotated corpus derived from 18th-century French encyclopedias.
  arXiv  Detail & Related papers  (2025-06-03T13:37:44Z)
• RanLayNet: A Dataset for Document Layout Detection used for Domain Adaptation and Generalization [36.973388673687815]
  RanLayNet is a synthetic document dataset enriched with automatically assigned labels. We show that a deep layout identification model trained on our dataset exhibits enhanced performance compared to a model trained solely on actual documents.
  arXiv  Detail & Related papers  (2024-04-15T07:50:15Z)
• WIKIGENBENCH: Exploring Full-length Wikipedia Generation under Real-World Scenario [32.28150998156827]
  WIKIGENBENCH is a new benchmark consisting of 1,320 entries.<n>For generation, we explore a real-world scenario where structured, full-length Wikipedia articles with citations are generated for new events using input documents from web sources.<n>For evaluation, we integrate systematic metrics and LLM-based metrics to assess the verifiability, organization, and other aspects aligned with real-world scenarios.
  arXiv  Detail & Related papers  (2024-02-28T11:51:56Z)
• Improving Long Document Topic Segmentation Models With Enhanced Coherence Modeling [19.303419410130672]
  We propose Topic-aware Sentence Structure Prediction (TSSP) and Contrastive Semantic Similarity Learning (CSSL) TSSP task is proposed to force the model to comprehend structural information by learning the original relations between adjacent sentences in a disarrayed document. CSSL objective is to ensure that the sentences representations in the same topic have higher similarity, while those in different topics are less similar.
  arXiv  Detail & Related papers  (2023-10-18T07:58:47Z)
• Cross-lingual Cross-temporal Summarization: Dataset, Models, Evaluation [20.675242617417677]
  Cross-lingual cross-temporal summarization (CLCTS) is a largely unexplored area that has the potential to improve cross-cultural accessibility and understanding. This paper comprehensively addresses the CLCTS task, including dataset creation, modeling, and evaluation.
  arXiv  Detail & Related papers  (2023-06-22T14:31:18Z)
• Revisiting the Evaluation of Image Synthesis with GANs [55.72247435112475]
  This study presents an empirical investigation into the evaluation of synthesis performance, with generative adversarial networks (GANs) as a representative of generative models. In particular, we make in-depth analyses of various factors, including how to represent a data point in the representation space, how to calculate a fair distance using selected samples, and how many instances to use from each set.
  arXiv  Detail & Related papers  (2023-04-04T17:54:32Z)
• Long Document Summarization with Top-down and Bottom-up Inference [113.29319668246407]
  We propose a principled inference framework to improve summarization models on two aspects. Our framework assumes a hierarchical latent structure of a document where the top-level captures the long range dependency. We demonstrate the effectiveness of the proposed framework on a diverse set of summarization datasets.
  arXiv  Detail & Related papers  (2022-03-15T01:24:51Z)
• MSeg: A Composite Dataset for Multi-domain Semantic Segmentation [100.17755160696939]
  We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. We reconcile the generalization and bring the pixel-level annotations into alignment by relabeling more than 220,000 object masks in more than 80,000 images. A model trained on MSeg ranks first on the WildDash-v1 leaderboard for robust semantic segmentation, with no exposure to WildDash data during training.
  arXiv  Detail & Related papers  (2021-12-27T16:16:35Z)
• Dynamic Hybrid Relation Network for Cross-Domain Context-Dependent Semantic Parsing [52.24507547010127]
  Cross-domain context-dependent semantic parsing is a new focus of research. We present a dynamic graph framework that effectively modelling contextual utterances, tokens, database schemas, and their complicated interaction as the conversation proceeds. The proposed framework outperforms all existing models by large margins, achieving new state-of-the-art performance on two large-scale benchmarks.
  arXiv  Detail & Related papers  (2021-01-05T18:11:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.