Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Lin, Xingtao, Qiu, Heqian, Wang, Lanxiao, Wang, Ruihang, Xu, Linfeng, Li, Hongliang
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866917841480974336
author Lin, Xingtao
Qiu, Heqian
Wang, Lanxiao
Wang, Ruihang
Xu, Linfeng
Li, Hongliang
author_facet Lin, Xingtao
Qiu, Heqian
Wang, Lanxiao
Wang, Ruihang
Xu, Linfeng
Li, Hongliang
contents Recent advancements in prompt tuning have successfully adapted large-scale models like Contrastive Language-Image Pre-trained (CLIP) for downstream tasks such as scene text detection. Typically, text prompt complements the text encoder's input, focusing on global features while neglecting fine-grained details, leading to fine-grained text being ignored in task of scene text detection. In this paper, we propose the region prompt tuning (RPT) method for fine-grained scene text detection, where region text prompt proposed would help focus on fine-grained features. Region prompt tuning method decomposes region text prompt into individual characters and splits visual feature map into region visual tokens, creating a one-to-one correspondence between characters and tokens. This allows a character matches the local features of a token, thereby avoiding the omission of detailed features and fine-grained text. To achieve this, we introduce a sharing position embedding to link each character with its corresponding token and employ a bidirectional distance loss to align each region text prompt character with the target ``text''. To refine the information at fine-grained level, we implement character-token level interactions before and after encoding. Our proposed method combines a general score map from the image-text process with a region score map derived from character-token matching, producing a final score map that could balance the global and local features and be fed into DBNet to detect the text. Experiments on benchmarks like ICDAR2015, TotalText, and CTW1500 demonstrate RPT impressive performance, underscoring its effectiveness for scene text detection.
format Preprint
id arxiv_https___arxiv_org_abs_2409_13576
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt
Lin, Xingtao
Qiu, Heqian
Wang, Lanxiao
Wang, Ruihang
Xu, Linfeng
Li, Hongliang
Computer Vision and Pattern Recognition
Artificial Intelligence
Recent advancements in prompt tuning have successfully adapted large-scale models like Contrastive Language-Image Pre-trained (CLIP) for downstream tasks such as scene text detection. Typically, text prompt complements the text encoder's input, focusing on global features while neglecting fine-grained details, leading to fine-grained text being ignored in task of scene text detection. In this paper, we propose the region prompt tuning (RPT) method for fine-grained scene text detection, where region text prompt proposed would help focus on fine-grained features. Region prompt tuning method decomposes region text prompt into individual characters and splits visual feature map into region visual tokens, creating a one-to-one correspondence between characters and tokens. This allows a character matches the local features of a token, thereby avoiding the omission of detailed features and fine-grained text. To achieve this, we introduce a sharing position embedding to link each character with its corresponding token and employ a bidirectional distance loss to align each region text prompt character with the target ``text''. To refine the information at fine-grained level, we implement character-token level interactions before and after encoding. Our proposed method combines a general score map from the image-text process with a region score map derived from character-token matching, producing a final score map that could balance the global and local features and be fed into DBNet to detect the text. Experiments on benchmarks like ICDAR2015, TotalText, and CTW1500 demonstrate RPT impressive performance, underscoring its effectiveness for scene text detection.
title Region Prompt Tuning: Fine-grained Scene Text Detection Utilizing Region Text Prompt
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2409.13576