MixTex: Unambiguous Recognition Should Not Rely Solely on Real Data

• URL: http://arxiv.org/abs/2406.17148v2
• Date: Tue, 9 Jul 2024 22:17:26 GMT
• Title: MixTex: Unambiguous Recognition Should Not Rely Solely on Real Data
• Authors: Renqing Luo, Yuhan Xu,
• Abstract summary: This paper introduces MixTex, an end-to-end OCR model designed for low-bias multilingual recognition. We identify specific recognition bias issues, such as the frequent misinterpretation of $e-t$ as $e-t$. We propose an innovative data augmentation method to mitigate this bias.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper introduces MixTex, an end-to-end LaTeX OCR model designed for low-bias multilingual recognition, along with its novel data collection method. In applying Transformer architectures to LaTeX text recognition, we identified specific bias issues, such as the frequent misinterpretation of $e-t$ as $e^{-t}$. We attribute this bias to the characteristics of the arXiv dataset commonly used for training. To mitigate this bias, we propose an innovative data augmentation method. This approach introduces controlled noise into the recognition targets by blending genuine text with pseudo-text and incorporating a small proportion of disruptive characters. We further suggest that this method has broader applicability to various disambiguation recognition tasks, including the accurate identification of erroneous notes in musical performances. MixTex's architecture leverages the Swin Transformer as its encoder and RoBERTa as its decoder. Our experimental results demonstrate that this approach significantly reduces bias in recognition tasks. Notably, when processing clear and unambiguous images, the model adheres strictly to the image rather than over-relying on contextual cues for token prediction.

Related papers

• Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing [71.29488677105127]
  Existing scene text recognition (STR) methods struggle to recognize challenging texts, especially for artistic and severely distorted characters. We propose a contrastive learning-based STR framework by leveraging synthetic and real unlabeled data without any human cost. Our method achieves SOTA performance (94.7% and 70.9% average accuracy on common benchmarks and Union14M-Benchmark.
  arXiv  Detail & Related papers  (2024-11-23T15:24:47Z)
• Learning Robust Named Entity Recognizers From Noisy Data With Retrieval Augmentation [67.89838237013078]
  Named entity recognition (NER) models often struggle with noisy inputs. We propose a more realistic setting in which only noisy text and its NER labels are available. We employ a multi-view training framework that improves robust NER without retrieving text during inference.
  arXiv  Detail & Related papers  (2024-07-26T07:30:41Z)
• When Text and Images Don't Mix: Bias-Correcting Language-Image Similarity Scores for Anomaly Detection [35.09035417676343]
  We show that the embeddings of text inputs unexpectedly tightly cluster together, far away from image embeddings, contrary to the model's contrastive training objective. We propose a novel methodology called BLISS which directly accounts for this similarity bias through the use of an auxiliary, external set of text inputs.
  arXiv  Detail & Related papers  (2024-07-24T08:20:02Z)
• AITTI: Learning Adaptive Inclusive Token for Text-to-Image Generation [53.65701943405546]
  We learn adaptive inclusive tokens to shift the attribute distribution of the final generative outputs. Our method requires neither explicit attribute specification nor prior knowledge of the bias distribution. Our method achieves comparable performance to models that require specific attributes or editing directions for generation.
  arXiv  Detail & Related papers  (2024-06-18T17:22:23Z)
• Is it an i or an l: Test-time Adaptation of Text Line Recognition Models [9.149602257966917]
  We introduce the problem of adapting text line recognition models during test time. We propose an iterative self-training approach that uses feedback from the language model to update the optical model. Experimental results show that the proposed adaptation method offers an absolute improvement of up to 8% in character error rate.
  arXiv  Detail & Related papers  (2023-08-29T05:44:00Z)
• Towards General Visual-Linguistic Face Forgery Detection [95.73987327101143]
  Deepfakes are realistic face manipulations that can pose serious threats to security, privacy, and trust. Existing methods mostly treat this task as binary classification, which uses digital labels or mask signals to train the detection model. We propose a novel paradigm named Visual-Linguistic Face Forgery Detection(VLFFD), which uses fine-grained sentence-level prompts as the annotation.
  arXiv  Detail & Related papers  (2023-07-31T10:22:33Z)
• Transformer-Based UNet with Multi-Headed Cross-Attention Skip Connections to Eliminate Artifacts in Scanned Documents [0.0]
  A modified UNet structure using a Swin Transformer backbone is presented to remove typical artifacts in scanned documents. An improvement in text extraction quality with a reduced error rate of up to 53.9% on the synthetic data is archived.
  arXiv  Detail & Related papers  (2023-06-05T12:12:23Z)
• ClipCrop: Conditioned Cropping Driven by Vision-Language Model [90.95403416150724]
  We take advantage of vision-language models as a foundation for creating robust and user-intentional cropping algorithms. We develop a method to perform cropping with a text or image query that reflects the user's intention as guidance. Our pipeline design allows the model to learn text-conditioned aesthetic cropping with a small dataset.
  arXiv  Detail & Related papers  (2022-11-21T14:27:07Z)
• Syntax-Aware Network for Handwritten Mathematical Expression Recognition [53.130826547287626]
  Handwritten mathematical expression recognition (HMER) is a challenging task that has many potential applications. Recent methods for HMER have achieved outstanding performance with an encoder-decoder architecture. We propose a simple and efficient method for HMER, which is the first to incorporate syntax information into an encoder-decoder network.
  arXiv  Detail & Related papers  (2022-03-03T09:57:19Z)
• One-shot Compositional Data Generation for Low Resource Handwritten Text Recognition [10.473427493876422]
  Low resource Handwritten Text Recognition is a hard problem due to the scarce annotated data and the very limited linguistic information. In this paper we address this problem through a data generation technique based on Bayesian Program Learning. Contrary to traditional generation approaches, which require a huge amount of annotated images, our method is able to generate human-like handwriting using only one sample of each symbol from the desired alphabet.
  arXiv  Detail & Related papers  (2021-05-11T18:53:01Z)
• Robust Document Representations using Latent Topics and Metadata [17.306088038339336]
  We propose a novel approach to fine-tuning a pre-trained neural language model for document classification problems. We generate document representations that capture both text and metadata artifacts in a task manner. Our solution also incorporates metadata explicitly rather than just augmenting them with text.
  arXiv  Detail & Related papers  (2020-10-23T21:52:38Z)

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.