Dichotomous Image Segmentation with Frequency Priors
Authors: Yan Zhou, Bo Dong, Yuanfeng Wu, Wentao Zhu, Geng Chen, Yanning Zhang
IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experiments on the benchmark dataset, DIS5K, demonstrate that our FP-DIS outperforms state-of-the-art methods by a large margin in terms of key evaluation metrics. |
| Researcher Affiliation | Academia | Yan Zhou1,4 , Bo Dong2 , Yuanfeng Wu3 , Wentao Zhu3 , Geng Chen4 and Yanning Zhang4 1State Key Laboratory of Industrial Control Technology, College of Control Science and Engineering, Zhejiang University, China 2College of Biomedical Engineering and Instrumental Science, Zhejiang University, China 3Zhejiang Lab, China 4National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology, School of Computer Science and Engineering, Northwestern Polytechnical University, China |
| Pseudocode | No | The paper includes architectural diagrams but does not contain any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | Our code is available at https://github.com/dongbo811/FP-DIS. |
| Open Datasets | Yes | Dataset. We performed extensive experiments on a large-scale benchmark dataset, DIS5K [Qin et al., 2022], which contains a total of 5,470 images from 225 categories. |
| Dataset Splits | Yes | The entire dataset is divided into three subsets: DIS-TR, DIS-VD and DIS-TE. DIS-TR and DIS-VD contain 3,000 training images and 470 validation images, respectively. DIS-TE is further split into four subsets (DIS-TE1, 2, 3, 4) with ascending shape complexities, each containing 500 images. |
| Hardware Specification | Yes | The model is implemented with the Pytorch framework on an A100 GPU. |
| Software Dependencies | No | The paper mentions 'Pytorch framework' but does not specify a version number for it or any other software dependencies. |
| Experiment Setup | Yes | In the training stage, the Res Net-50 [He et al., 2016] is pre-trained on Image Net-1K [Deng et al., 2009], the rest of the modules are initialized randomly. And we use the Adam optimizer with an initial learning rate of 1e-4, decaying by 10 every 50 epochs. The number of training epochs is set to 200. The resampled images with a size of 1024 1024 are fed into the proposed FP-DIS to get segmentation results in an end-to-end manner. |