ClusterTabNet: Supervised clustering method for table detection and table structure recognition

2024-02-12 · Marek Polewczyk, Marco Spinaci

We present a novel deep-learning-based method to cluster words in documents which we apply to detect and recognize tables given the OCR output. We interpret table structure bottom-up as a graph of relations between pairs of words (belonging to the same row, column, header, as well as to the same table) and use a transformer encoder model to predict its adjacency matrix. We demonstrate the performance of our method on the PubTables-1M dataset as well as PubTabNet and FinTabNet datasets. Compared to the current state-of-the-art detection methods such as DETR and Faster R-CNN, our method achieves similar or better accuracy, while requiring a significantly smaller model.

📄 PDF Abstract BibTeX arXiv:2402.07502

Code (1)

sap-samples/clustertabnet 공식 구현 pytorch

Tasks

ClusteringOptical Character Recognition (OCR)Table Detection

Methods 이 논문이 사용한 방법론

Position-Wise Feed-Forward Layer 설명 없음

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…

BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Attention 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Multi-Head Attention 설명 없음

Postulating Exoplanetary Habitability via a Novel Anomaly Detection Method

2021-09-06 · Jyotirmoy Sarkar, Kartik Bhatia, Snehanshu Saha, Margarita Safonova 외

A profound shift in the study of cosmology came with the discovery of thousands of exoplanets and the possibility of the existence of billions of them in our Galaxy. The biggest goal in these searches is whether there ar…

Anomaly Detection Clustering

Multimodal Clustering for Community Detection

2017-02-27 · Dmitry I. Ignatov, Alexander Semenov, Daria Komissarova, Dmitry V. Gnatyshak

Multimodal clustering is an unsupervised technique for mining interesting patterns in $n$-adic binary relations or $n$-mode networks. Among different types of such generalized patterns one can find biclusters and formal …

Attribute Clustering Community Detection

Using Decision Trees for Interpretable Supervised Clustering

2023-07-16 · Natallia Kokash, Leonid Makhnist

In this paper, we address an issue of finding explainable clusters of class-uniform data in labelled datasets. The issue falls into the domain of interpretable supervised clustering. Unlike traditional clustering, superv…

Clustering

Deep unsupervised anomaly detection

2021-01-05 · Winter Conference on Applications of Computer Vision 2021 1 · Tangqing Li, Zheng Wang, Siying Liu, Wen-Yan Lin

This paper proposes a novel method to detect anomalies in large datasets under a fully unsupervised setting. The key idea behind our algorithm is to learn the representation underlying normal data. To this end, we levera…

Anomaly Detection Clustering Representation Learning Unsupervised Anomaly Detection+5

Deep End-to-end Unsupervised Anomaly Detection

2019-09-25 · Li Tangqing, Wang Zheng, Liu Siying, Daniel Lin Wen-Yan

Anomaly Detection Clustering Representation Learning Unsupervised Anomaly Detection