Mitigating Long-tail Distribution in Oracle Bone Inscriptions: Dataset, Model, and Benchmark

• URL: http://arxiv.org/abs/2504.09555v2
• Date: Wed, 16 Apr 2025 09:29:01 GMT
• Title: Mitigating Long-tail Distribution in Oracle Bone Inscriptions: Dataset, Model, and Benchmark
• Authors: Jinhao Li, Zijian Chen, Runze Jiang, Tingzhu Chen, Changbo Wang, Guangtao Zhai,
• Abstract summary: oracle bone inscription (OBI) recognition plays a significant role in understanding the history and culture of ancient China.<n>The existing OBI datasets suffer from a long-tail distribution problem, leading to biased performance of OBI recognition models across majority and minority classes.<n>We present the Oracle-P15K, a structure-aligned OBI dataset for OBI generation and denoising, consisting of 14,542 images infused with domain knowledge from OBI experts.
• Score: 36.21507457913964
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The oracle bone inscription (OBI) recognition plays a significant role in understanding the history and culture of ancient China. However, the existing OBI datasets suffer from a long-tail distribution problem, leading to biased performance of OBI recognition models across majority and minority classes. With recent advancements in generative models, OBI synthesis-based data augmentation has become a promising avenue to expand the sample size of minority classes. Unfortunately, current OBI datasets lack large-scale structure-aligned image pairs for generative model training. To address these problems, we first present the Oracle-P15K, a structure-aligned OBI dataset for OBI generation and denoising, consisting of 14,542 images infused with domain knowledge from OBI experts. Second, we propose a diffusion model-based pseudo OBI generator, called OBIDiff, to achieve realistic and controllable OBI generation. Given a clean glyph image and a target rubbing-style image, it can effectively transfer the noise style of the original rubbing to the glyph image. Extensive experiments on OBI downstream tasks and user preference studies show the effectiveness of the proposed Oracle-P15K dataset and demonstrate that OBIDiff can accurately preserve inherent glyph structures while transferring authentic rubbing styles effectively.

Related papers

• OBIFormer: A Fast Attentive Denoising Framework for Oracle Bone Inscriptions [7.657419462547438]
  Oracle bone inscriptions (OBIs) are the earliest known form of Chinese characters and serve as a valuable resource for research in anthropology and archaeology. Previous methods either focus on pixel-level information or utilize vanilla transformers for glyph-based OBI denoising. This paper proposes a fast attentive denoising framework for oracle bone inscriptions, i.e., OBIFormer.
  arXiv  Detail & Related papers  (2025-04-18T07:24:35Z)
• OBI-Bench: Can LMMs Aid in Study of Ancient Script on Oracle Bones? [40.226986425846825]
  We introduce OBI-Bench, a holistic benchmark crafted to evaluate large multi-modal models (LMMs) on whole-process oracle bone inscriptions.<n> OBI-Bench includes 5,523 meticulously collected diverse-sourced images, covering five key domain problems: recognition, rejoining, classification, retrieval, and deciphering.<n>Unlike existing benchmarks, OBI-Bench focuses on advanced visual perception and reasoning with OBI-specific knowledge, challenging LMMs to perform tasks akin to those faced by experts.
  arXiv  Detail & Related papers  (2024-12-02T06:31:28Z)
• Unsupervised Attention Regularization Based Domain Adaptation for Oracle Character Recognition [59.05212866862219]
  The study of oracle characters plays an important role in Chinese archaeology and philology. The difficulty of collecting and annotating real-world scanned oracle characters hinders the development of oracle character recognition. We develop a novel unsupervised domain adaptation (UDA) method to transfer recognition knowledge from labeled handprinted oracle characters to unlabeled scanned data.
  arXiv  Detail & Related papers  (2024-09-24T09:07:05Z)
• Oracle Bone Inscriptions Multi-modal Dataset [58.20314888996118]
  Oracle bone inscriptions(OBI) is the earliest developed writing system in China, bearing invaluable written exemplifications of early Shang history and paleography. This paper proposes an Oracle Bone Inscriptions Multi-modal dataset, which includes annotation information for 10,077 pieces of oracle bones. This dataset can be used for a variety of AI-related research tasks relevant to the field of OBI, such as OBI Character Detection and Recognition, Rubbing Denoising, Character Matching, Character Generation, Reading Sequence Prediction, Missing Characters Completion task and so on.
  arXiv  Detail & Related papers  (2024-07-04T12:47:32Z)
• Improving Biomedical Entity Linking with Retrieval-enhanced Learning [53.24726622142558]
  $k$NN-BioEL provides a BioEL model with the ability to reference similar instances from the entire training corpus as clues for prediction. We show that $k$NN-BioEL outperforms state-of-the-art baselines on several datasets.
  arXiv  Detail & Related papers  (2023-12-15T14:04:23Z)
• Oracle Character Recognition using Unsupervised Discriminative Consistency Network [65.64172835624206]
  We propose a novel unsupervised domain adaptation method for oracle character recognition (OrCR) We leverage pseudo-labeling to incorporate the semantic information into adaptation and constrain augmentation consistency. Our approach achieves state-of-the-art result on Oracle-241 dataset and substantially outperforms the recently proposed structure-texture separation network by 15.1%.
  arXiv  Detail & Related papers  (2023-12-11T02:52:27Z)
• Recognition of Oracle Bone Inscriptions by using Two Deep Learning Models [0.0]
  Oracle bone inscriptions (OBIs) contain some of the oldest characters in the world and were used in China about 3000 years ago. This paper aims to design a online OBI recognition system for helping preservation and organization the cultural heritage.
  arXiv  Detail & Related papers  (2021-05-03T12:31:57Z)
• MOGAN: Morphologic-structure-aware Generative Learning from a Single Image [59.59698650663925]
  Recently proposed generative models complete training based on only one image. We introduce a MOrphologic-structure-aware Generative Adversarial Network named MOGAN that produces random samples with diverse appearances. Our approach focuses on internal features including the maintenance of rational structures and variation on appearance.
  arXiv  Detail & Related papers  (2021-03-04T12:45:23Z)
• Improving Learning Effectiveness For Object Detection and Classification in Cluttered Backgrounds [6.729108277517129]
  This paper develops a framework that permits to autonomously generate a training dataset in heterogeneous cluttered backgrounds. It is clear that the learning effectiveness of the proposed framework should be improved in complex and heterogeneous environments. The performance of the proposed framework is investigated through empirical tests and compared with that of the model trained with the COCO dataset.
  arXiv  Detail & Related papers  (2020-02-27T22:28:48Z)

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.