EUVIMEDEUVIMED entdecken
Crossref

Turning a CLIP Model Into a Scene Text Spotter

Wenwen Yu, Yuliang Liu, Xingkui Zhu, Haoyu Cao, Xing Sun, Xiang Bai

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2024-09 · 46 (9) · 6040-6054

DOI: 10.1109/tpami.2024.3379828 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024-09. Verfasst von Wenwen Yu und 5 weiteren Autor:innen. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 98 Literaturangaben. Gefördert von: National Natural Science Foundation of China, National Key Research and Development Program of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We exploit the potential of the large-scale Contrastive Language-Image Pretraining (CLIP) model to enhance scene text detection and spotting tasks, transforming it into a robust backbone, FastTCM-CR50. This backbone utilizes visual prompt learning and cross-attention in CLIP to extract image and text-based prior knowledge. Using predefined and learnable prompts, FastTCM-CR50 introduces an instance-language matching process to enhance the synergy between image and text embeddings, thereby refining text regions. Our Bimodal Similarity Matching (BSM) module facilitates dynamic language prompt generation, enabling offline computations and improving performance. FastTCM-CR50 offers several advantages: 1) It can enhance existing text detectors and spotters, improving performance by an average of 1.6% and 1.5%, respectively. 2) It outperforms the previous TCM-CR50 backbone, yielding an average improvement of 0.2% and 0.55% in text detection and spotting tasks, along with a 47.1% increase in inference speed. 3) It showcases robust few-shot training capabilities. Utilizing only 10% of the supervised data, FastTCM-CR50 improves performance by an average of 26.5% and 4.7% for text detection and spotting tasks, respectively. 4) It consistently enhances performance on out-of-distribution text detection and spotting datasets, particularly the NightTime-ArT subset from ICDAR2019-ArT and the DOTA dataset for oriented object detection.

Förderung

  • National Natural Science Foundation of China
  • National Key Research and Development Program of China

Zitieren

APA

Yu, W., Liu, Y., Zhu, X., Cao, H., Sun, X., & Bai, X. (2024). Turning a CLIP Model Into a Scene Text Spotter. IEEE Transactions on Pattern Analysis and Machine Intelligence, 46(9), 6040-6054. https://doi.org/10.1109/tpami.2024.3379828

Vancouver

Yu W, Liu Y, Zhu X, Cao H, Sun X, Bai X. Turning a CLIP Model Into a Scene Text Spotter. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2024;46(9):6040-6054. doi:10.1109/tpami.2024.3379828

BibTeX
@article{Yu2024,
  author = {Yu, Wenwen and Liu, Yuliang and Zhu, Xingkui and Cao, Haoyu and Sun, Xing and Bai, Xiang},
  title = {Turning a CLIP Model Into a Scene Text Spotter},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2024},
  volume = {46},
  number = {9},
  pages = {6040--6054},
  doi = {10.1109/tpami.2024.3379828}
}
Kostenlos starten →