Pith. sign in

REVIEW 3 cited by

PP-OCRv2: Bag of Tricks for Ultra Lightweight OCR System

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2109.03144 v2 pith:3POX4UYO submitted 2021-09-07 cs.CV

Yuning Du , Chenxia Li , Ruoyu Guo , Cheng Cui , Weiwei Liu , Jun Zhou , Bin Lu , Yehua Yang
show 4 more authors
Qiwen Liu Xiaoguang Hu Dianhai Yu Yanjun Ma
This is my paper · ORCID
classification cs.CV
keywords pp-ocrsystemlightweightpp-ocrv2accuracybetterefficiencylearning
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Optical Character Recognition (OCR) systems have been widely used in various of application scenarios. Designing an OCR system is still a challenging task. In previous work, we proposed a practical ultra lightweight OCR system (PP-OCR) to balance the accuracy against the efficiency. In order to improve the accuracy of PP-OCR and keep high efficiency, in this paper, we propose a more robust OCR system, i.e. PP-OCRv2. We introduce bag of tricks to train a better text detector and a better text recognizer, which include Collaborative Mutual Learning (CML), CopyPaste, Lightweight CPUNetwork (LCNet), Unified-Deep Mutual Learning (U-DML) and Enhanced CTCLoss. Experiments on real data show that the precision of PP-OCRv2 is 7% higher than PP-OCR under the same inference cost. It is also comparable to the server models of the PP-OCR which uses ResNet series as backbones. All of the above mentioned models are open-sourced and the code is available in the GitHub repository PaddleOCR which is powered by PaddlePaddle.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. GDI-Bench: A Benchmark for General Document Intelligence with Vision and Reasoning Decoupling

    cs.CL 2025-04 conditional novelty 6.0 of 10

    A document-intelligence benchmark decouples visual and reasoning complexity, and a parameter-freezing fine-tuning method improves an 8B model without catastrophic forgetting.

  2. A Multimodal Pipeline for Clinical Data Extraction: Applying Vision-Language Models to Scans of Transfusion Reaction Reports

    cs.CL 2025-04 conditional novelty 5.0 of 10

    A YOLO checkbox detector plus a zero-shot Pixtral vision-language model extracted checked categories from scanned transfusion reaction reports with roughly 92% F1 score, outperforming an OCR-plus-Levenshtein baseline (85%).

  3. Ocean-OCR: Towards General OCR Application via a Vision-Language Model

    cs.CV 2025-01 conditional novelty 4.0 of 10

    A 3B vision-language model trained with a large OCR-heavy data mix reports top scores on OCR benchmarks and beats the TextIn and PaddleOCR engines on custom document, scene-text, and handwriting evaluations.

Pith tools