Joint Low-level and High-level Textual Representation Learning with Multiple Masking Strategies

• URL: http://arxiv.org/abs/2505.06855v1
• Date: Sun, 11 May 2025 05:52:55 GMT
• Title: Joint Low-level and High-level Textual Representation Learning with Multiple Masking Strategies
• Authors: Zhengmi Tang, Yuto Mitsui, Tomo Miyazaki, Shinichiro Omachi,
• Abstract summary: Synthetic images cannot faithfully reproduce real-world scenarios, resulting in performance disparities when handling complex real-world images.<n>Recent self-supervised learning techniques, notably contrastive learning and masked image modeling, narrow this domain gap by exploiting unlabeled real text images.<n>Our Multi-Masking Strategy (MMS) integrates random patch, blockwise, and span masking into the MIM frame, which jointly learns low and high-level textual representations.
• Score: 3.7498611358320733
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Most existing text recognition methods are trained on large-scale synthetic datasets due to the scarcity of labeled real-world datasets. Synthetic images, however, cannot faithfully reproduce real-world scenarios, such as uneven illumination, irregular layout, occlusion, and degradation, resulting in performance disparities when handling complex real-world images. Recent self-supervised learning techniques, notably contrastive learning and masked image modeling (MIM), narrow this domain gap by exploiting unlabeled real text images. This study first analyzes the original Masked AutoEncoder (MAE) and observes that random patch masking predominantly captures low-level textural features but misses high-level contextual representations. To fully exploit the high-level contextual representations, we introduce random blockwise and span masking in the text recognition task. These strategies can mask the continuous image patches and completely remove some characters, forcing the model to infer relationships among characters within a word. Our Multi-Masking Strategy (MMS) integrates random patch, blockwise, and span masking into the MIM frame, which jointly learns low and high-level textual representations. After fine-tuning with real data, MMS outperforms the state-of-the-art self-supervised methods in various text-related tasks, including text recognition, segmentation, and text-image super-resolution.

Related papers

• Knowing Where to Focus: Attention-Guided Alignment for Text-based Person Search [64.15205542003056]
  We introduce Attention-Guided Alignment (AGA) framework featuring two innovative components: Attention-Guided Mask (AGM) Modeling and Text Enrichment Module (TEM)<n>AGA achieves new state-of-the-art results with Rank-1 accuracy reaching 78.36%, 67.31%, and 67.4% on CUHK-PEDES, ICFG-PEDES, and RSTP, respectively.
  arXiv  Detail & Related papers  (2024-12-19T17:51:49Z)
• TextCoT: Zoom In for Enhanced Multimodal Text-Rich Image Understanding [91.30065932213758]
  Large Multimodal Models (LMMs) have sparked a surge in research aimed at harnessing their remarkable reasoning abilities. We propose TextCoT, a novel Chain-of-Thought framework for text-rich image understanding. Our method is free of extra training, offering immediate plug-and-play functionality.
  arXiv  Detail & Related papers  (2024-04-15T13:54:35Z)
• Class-Aware Mask-Guided Feature Refinement for Scene Text Recognition [56.968108142307976]
  We propose a novel approach called Class-Aware Mask-guided feature refinement (CAM) Our approach introduces canonical class-aware glyph masks to suppress background and text style noise. By enhancing the alignment between the canonical mask feature and the text feature, the module ensures more effective fusion.
  arXiv  Detail & Related papers  (2024-02-21T09:22:45Z)
• Open-Vocabulary Segmentation with Unpaired Mask-Text Supervision [87.15580604023555]
  Unpair-Seg is a novel weakly-supervised open-vocabulary segmentation framework. It learns from unpaired image-mask and image-text pairs, which can be independently and efficiently collected. It achieves 14.6% and 19.5% mIoU on the ADE-847 and PASCAL Context-459 datasets.
  arXiv  Detail & Related papers  (2024-02-14T06:01:44Z)
• CtxMIM: Context-Enhanced Masked Image Modeling for Remote Sensing Image Understanding [38.53988682814626]
  We propose a context-enhanced masked image modeling method (CtxMIM) for remote sensing image understanding. CtxMIM formulates original image patches as a reconstructive template and employs a Siamese framework to operate on two sets of image patches. With the simple and elegant design, CtxMIM encourages the pre-training model to learn object-level or pixel-level features on a large-scale dataset.
  arXiv  Detail & Related papers  (2023-09-28T18:04:43Z)
• Self-supervised Scene Text Segmentation with Object-centric Layered Representations Augmented by Text Regions [22.090074821554754]
  We propose a self-supervised scene text segmentation algorithm with layered decoupling of representations derived from the object-centric manner to segment images into texts and background. On several public scene text datasets, our method outperforms the state-of-the-art unsupervised segmentation algorithms.
  arXiv  Detail & Related papers  (2023-08-25T05:00:05Z)
• TextDiff: Mask-Guided Residual Diffusion Models for Scene Text Image Super-Resolution [17.95994419104427]
  TextDiff is a diffusion-based framework tailored for scene text image super-resolution.<n>It achieves state-of-the-art (SOTA) performance on public benchmark datasets.<n>Our proposed MRD module is plug-and-play that effectively sharpens the text edges produced by SOTA methods.
  arXiv  Detail & Related papers  (2023-08-13T11:02:16Z)
• Multi-Modal Representation Learning with Text-Driven Soft Masks [48.19806080407593]
  We propose a visual-linguistic representation learning approach within a self-supervised learning framework. We generate diverse features for the image-text matching (ITM) task via soft-masking the regions in an image. We identify the relevant regions to each word by computing the word-conditional visual attention using multi-modal encoder.
  arXiv  Detail & Related papers  (2023-04-03T05:07:49Z)
• Self-supervised Character-to-Character Distillation for Text Recognition [54.12490492265583]
  We propose a novel self-supervised Character-to-Character Distillation method, CCD, which enables versatile augmentations to facilitate text representation learning. CCD achieves state-of-the-art results, with average performance gains of 1.38% in text recognition, 1.7% in text segmentation, 0.24 dB (PSNR) and 0.0321 (SSIM) in text super-resolution.
  arXiv  Detail & Related papers  (2022-11-01T05:48:18Z)
• Language Matters: A Weakly Supervised Pre-training Approach for Scene Text Detection and Spotting [69.77701325270047]
  This paper presents a weakly supervised pre-training method that can acquire effective scene text representations. Our network consists of an image encoder and a character-aware text encoder that extract visual and textual features. Experiments show that our pre-trained model improves F-score by +2.5% and +4.8% while transferring its weights to other text detection and spotting networks.
  arXiv  Detail & Related papers  (2022-03-08T08:10:45Z)
• Stroke-Based Scene Text Erasing Using Synthetic Data [0.0]
  Scene text erasing can replace text regions with reasonable content in natural images. The lack of a large-scale real-world scene-text removal dataset allows the existing methods to not work in full strength. We enhance and make full use of the synthetic text and consequently train our model only on the dataset generated by the improved synthetic text engine. This model can partially erase text instances in a scene image with a bounding box provided or work with an existing scene text detector for automatic scene text erasing.
  arXiv  Detail & Related papers  (2021-04-23T09:29:41Z)

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.