paper-with-me

Papers

DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning

2025-01-01 · CVPR 2025 1 · Xiao-Hui Li, Fei Yin, Cheng-Lin Liu

Document image segmentation is crucial in document analysis and recognition but remains challenging due to the heterogeneity of document formats and diverse segmentation tasks. Existing methods often treat these tasks separately, leading to limited generalization and resource wastage.This paper introduces DocSAM, a transformer-based unified framework for various document image segmentation tasks, including document layout analysis, multi-granularity text segmentation, and table structure recognition by modelling these tasks as a combination of instance and semantic segmentation.Specifically, DocSAM uses a Sentence BERT to map category names from each dataset into semantic queries of the same dimension as instance queries. These queries interact through attention mechanisms and are cross-attended with image features to predict instance and semantic segmentation masks. To predict instance categories, instance queries are dot-producted with semantic queries, and scores are normalized using softmax.As a result, DocSAM can be jointly trained on heterogeneous datasets, enhancing robustness and generalization while reducing computing and storage resources. Comprehensive evaluations show that DocSAM outperforms existing methods in accuracy, efficiency, and adaptability, highlighting its potential for advancing document image understanding and segmentation in various applications.

📄 PDF Abstract BibTeX

Code (0)

등록된 구현이 없습니다.

Tasks

Document Layout AnalysisImage SegmentationSegmentationSemantic SegmentationSentenceText Segmentation

Methods 이 논문이 사용한 방법론

Refunds@Expedia|||How do I get a full refund from Expedia? “How do I get a full refund from Expedia? How do I get a full refund from Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Quick Help &…
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention 설명 없음
Attention Dropout Attention Dropout is a type of dropout used in attention-based architectures, where elements are randomly dropped out of the…
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
WordPiece 설명 없음
Weight Decay 설명 없음
Multi-Head Attention 설명 없음

Similar Papers 제목 키워드 기반

SwinDocSegmenter: An End-to-End Unified Domain Adaptive Transformer for Document Instance Segmentation

2023-05-08 · Ayan Banerjee, Sanket Biswas, Josep Lladós, Umapada Pal

Instance-level segmentation of documents consists in assigning a class-aware and instance-aware label to each pixel of the image. It is a key step in document parsing for their understanding. In this paper, we present a …

DecoderInstance SegmentationSegmentationSemantic Segmentation

Mixed-Query Transformer: A Unified Image Segmentation Architecture

2024-04-06 · Pei Wang, Zhaowei Cai, Hao Yang, Ashwin Swaminathan 외

Existing unified image segmentation models either employ a unified architecture across multiple tasks but use separate weights tailored to each dataset, or apply a single set of weights to multiple datasets but are limit…

Data AugmentationImage SegmentationSegmentationSemantic Segmentation

CMRAG: Co-modality-based visual document retrieval and question answering

2025-09-02 · Wang Chen, Wenhan Yu, Guanqiang Qi, Weikang Li 외 arxiv

Retrieval-Augmented Generation (RAG) has become a core paradigm in document question answering tasks. However, existing methods have limitations when dealing with multimodal documents: one category of methods relies on l…

Question Answering

Query by String word spotting based on character bi-gram indexing

2015-05-28 · Suman K. Ghosh, Ernest Valveny

In this paper we propose a segmentation-free query by string word spotting method. Both the documents and query strings are encoded using a recently proposed word representa- tion that projects images and strings into a …

AttributeRe-RankingRetrievalSegmentation

DEPT: Document Embedding Preservation Tuning for Unified Query Expansion and Retrieval

2026-08-18 · Jingyuan Wang, Richong Zhang, Zhijie Nie, Mingxin Li 외 arxiv

Large language models (LLMs) can both expand underspecified queries and encode text as dense representations, suggesting a unified model for query expansion and retrieval. Existing systems usually rely on prompted expans…