Omnidirectional Scene Text Detection with Sequential-free Box Discretization
Authors: Yuliang Liu, Sheng Zhang, Lianwen Jin, Lele Xie, Yaqiang Wu, Zhepeng Wang
IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments showed that the proposed method can outperform state-of-the-art methods in many popular scene text benchmarks, including ICDAR 2015, MLT, and MSRA-TD500. Ablation study also showed that simply integrating the SBD into Mask R-CNN framework, the detection performance can be substantially improved. |
| Researcher Affiliation | Collaboration | Yuliang Liu1 , Sheng Zhang1 , Lianwen Jin1 , Lele Xie1 , Yaqiang Wu2 and Zhepeng Wang2 1School of Electronic and Information Engineering, South China University of Technology, China 2Lenovo Inc, China |
| Pseudocode | No | The paper describes the methodology but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about open-source code availability or a link to a code repository. |
| Open Datasets | Yes | We used synthetic data [Gupta et al., 2016] to pretrain the model and finetuned on the provided training data from MLT [Nayef et al., 2017], and ICDAR 2015 [Karatzas and Gomez Bigorda, 2015]. For MSRA-TD500 [Yao et al., 2012]...pretrained the model from 4k well annotated samples from [Shi et al., 2017a] |
| Dataset Splits | Yes | ICDAR 2017 MLT...including 7.2k training samples, 1.8k validation samples and 9k testing samples. MSRA-TD500...with 300 training images and 200 testing images. ICDAR 2015 Incidental Scene Text...contains 1k training samples and 500 testing samples. HRSC2016 dataset...436, 181, and 444 images for training, validating, and testing set, respectively. |
| Hardware Specification | Yes | The number of maximum iterations is 40 epochs for each dataset on four NVIDIA 1080ti GPUs. |
| Software Dependencies | No | The paper does not provide specific version numbers for software dependencies or libraries used in the experiments. |
| Experiment Setup | Yes | The number of maximum iterations is 40 epochs for each dataset...The initial learning rate is 10 2 and reduces to 10 3 and 10 4 on the 25th and 32th epoch, respectively. In order to balance the learning weights of all branches, the weights of KEs and match-type learning are empirically restricted to 0.2 and 0.01, respectively. |