I3CL:Intra- and Inter-Instance Collaborative Learning for Arbitrary-shaped Scene Text Detection

3 Aug 2021  ·  Bo Du, Jian Ye, Jing Zhang, Juhua Liu, DaCheng Tao ·

Existing methods for arbitrary-shaped text detection in natural scenes face two critical issues, i.e., 1) fracture detections at the gaps in a text instance; and 2) inaccurate detections of arbitrary-shaped text instances with diverse background context. To address these issues, we propose a novel method named Intra- and Inter-Instance Collaborative Learning (I3CL). Specifically, to address the first issue, we design an effective convolutional module with multiple receptive fields, which is able to collaboratively learn better character and gap feature representations at local and long ranges inside a text instance. To address the second issue, we devise an instance-based transformer module to exploit the dependencies between different text instances and a global context module to exploit the semantic context from the shared background, which are able to collaboratively learn more discriminative text feature representation. In this way, I3CL can effectively exploit the intra- and inter-instance dependencies together in a unified end-to-end trainable framework. Besides, to make full use of the unlabeled data, we design an effective semi-supervised learning method to leverage the pseudo labels via an ensemble strategy. Without bells and whistles, experimental results show that the proposed I3CL sets new state-of-the-art results on three challenging public benchmarks, i.e., an F-measure of 77.5% on ICDAR2019-ArT, 86.9% on Total-Text, and 86.4% on CTW-1500. Notably, our I3CL with the ResNeSt-101 backbone ranked 1st place on the ICDAR2019-ArT leaderboard. The source code will be available at https://github.com/ViTAE-Transformer/ViTAE-Transformer-Scene-Text-Detection.

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Scene Text Detection SCUT-CTW1500 I3CL + SSL F-Measure 86.5 # 5
Precision 88.4 # 5
Recall 84.6 # 6
Scene Text Detection Total-Text I3CL + SSL(ResNet-50) F-Measure 86.9% # 6
Precision 89.8 # 7
Recall 84.2 # 7


No methods listed for this paper. Add relevant methods here