Sub-Band Based Attention for Robust Polyp Segmentation

Authors: Xianyong Fang, Yuqing Shi, Qingqing Guo, Linbo Wang, Zhengyi Liu

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental This section reports some experimental results. For the complete codes and more experimental settings, results and ablation studies, please check the supplementary document.
Researcher Affiliation Academia Xianyong Fang , Yuqing Shi , Qingqing Guo , Linbo Wang and Zhengyi Liu School of Computer Science and Technology, Anhui University fangxianyong@ahu.edu.cn, e21201044@stu.ahu.edu.cn, guoqingad@sina.com, {wanglb, liuzywen}@ahu.edu.cn
Pseudocode No The paper contains figures illustrating module structures and mathematical formulations but does not include structured pseudocode or algorithm blocks.
Open Source Code Yes For the complete codes and more experimental settings, results and ablation studies, please check the supplementary document.
Open Datasets Yes Five colonoscopy image datasets are adopted, including ETIS [Silva et al., 2014], CVC-Clinic DB [Bernal et al., 2015], CVC-Colon DB [Tajbakhsh et al., 2015], CVC300 [V azquez et al., 2017] and Kvasir [Jha et al., 2020].
Dataset Splits No The paper states: 'The training set contains 1450 images selected from Kvasir [Jha et al., 2020] and CVC-Clinic DB [Bernal et al., 2015] with all the left images taken as testing image.' This describes training and test splits, but no explicit validation split is detailed or mentioned with specific counts or percentages.
Hardware Specification Yes SBA-Net is implemented in Py Torch with the CUDA library, a Ge Force RTX 3090 Ti GPU and an Intel Core i712700KF Processor.
Software Dependencies No The paper mentions 'SBA-Net is implemented in Py Torch with the CUDA library,' but does not provide specific version numbers for PyTorch, CUDA, or other key software dependencies.
Experiment Setup Yes Adam optimizer is adopted with the learning rate 5e-5. Batch size is set to 8 with the epoch 80.