ARTS: Eliminating Inconsistency between Text Detection and Recognition with Auto-Rectification Text Spotter

2021-10-20 · Humen Zhong, Jun Tang, Wenhai Wang, Zhibo Yang, Cong Yao, Tong Lu

Recent approaches for end-to-end text spotting have achieved promising results. However, most of the current spotters were plagued by the inconsistency problem between text detection and recognition. In this work, we introduce and prove the existence of the inconsistency problem and analyze it from two aspects: (1) inconsistency of text recognition features between training and testing, and (2) inconsistency of optimization targets between text detection and recognition. To solve the aforementioned issues, we propose a differentiable Auto-Rectification Module (ARM) together with a new training strategy to enable propagating recognition loss back into detection branch, so that our detection branch can be jointly optimized by detection and recognition targets, which largely alleviates the inconsistency problem between text detection and recognition. Based on these designs, we present a simple yet robust end-to-end text spotting framework, termed Auto-Rectification Text Spotter (ARTS), to detect and recognize arbitrarily-shaped text in natural scenes. Extensive experiments demonstrate the superiority of our method. In particular, our ARTS-S achieves 77.1% end-to-end text spotting F-measure on Total-Text at a competitive speed of 10.5 FPS, which significantly outperforms previous methods in both accuracy and inference speed.

📄 PDF Abstract BibTeX arXiv:2110.10405

Code (0)

등록된 구현이 없습니다.

Tasks

Text Detection Text Spotting

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Diffusion Model is a Good Pose Estimator from 3D RF-Vision

2024-03-24 · Junqiao Fan, Jianfei Yang, Yuecong Xu, Lihua Xie

Human pose estimation (HPE) from Radio Frequency vision (RF-vision) performs human sensing using RF signals that penetrate obstacles without revealing privacy (e.g., facial information). Recently, mmWave radar has emerge…

Pose Estimation

Monocular 3D Object Detection via Feature Domain Adaptation

2020-08-01 · ECCV 2020 8 · Lele Chen, Guofeng Cui, Celong Liu, Zhong Li 외

Monocular 3D object detection is a challenging task due to unreliable depth, resulting in a distinct performance gap between monocular and LiDAR-based approaches. In this paper, we propose a novel domain adaptation based…

3D Object Detection Domain Adaptation Foreground Segmentation Monocular 3D Object Detection+3

DQE: A Semantic-Aware Evaluation Metric for Time Series Anomaly Detection

2026-03-06 · Yuewei Li, Dalin Zhang, Huan Li, Xinyi Gong 외 arxiv

Time series anomaly detection has achieved remarkable progress in recent years. However, evaluation practices have received comparatively less attention, despite their critical importance. Existing metrics exhibit severa…

Time Series Anomaly Detection

MV2UV: Generating High-quality UV Texture Maps with Multiview Prompts

2026-03-16 · Zheng Zhang, Qinchuan Zhang, Yuteng Ye, Zhi Chen 외 arxiv

Generating high-quality textures for 3D assets is a challenging task. Existing multiview texture generation methods suffer from the multiview inconsistency and missing textures on unseen parts, while UV inpainting textur…

Alleviating the Inconsistency Problem of Applying Graph Neural Network to Fraud Detection

2020-05-01 · Zhiwei Liu, Yingtong Dou, Philip S. Yu, Yutong Deng 외

The graph-based model can help to detect suspicious fraud online. Owing to the development of Graph Neural Networks~(GNNs), prior research work has proposed many GNN-based fraud detection frameworks based on either homog…

Fraud Detection Graph Neural Network Relation