RANet: Region Attention Network for Semantic Segmentation
Authors: Dingguo Shen, Yuanfeng Ji, Ping Li, Yi Wang, Di Lin
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We extensively evaluate our method on the challenging segmentation benchmarks, demonstrating that RANet effectively helps to achieve the state-of-the-art results. Code will be available at: https://github.com/dingguo1996/RANet. |
| Researcher Affiliation | Academia | Dingguo Shen1,2, , Yuanfeng Ji3, , Ping Li4, Yi Wang2, Di Lin1, 1Tianjin University, 2Shenzhen University, 3The University of Hong Kong, 4The Hong Kong Polytechnic University |
| Pseudocode | No | No pseudocode or algorithm blocks are present. The paper describes the methods using text, equations, and diagrams. |
| Open Source Code | Yes | Code will be available at: https://github.com/dingguo1996/RANet. |
| Open Datasets | Yes | We conduct the experiments on the Cityscapes, PASCAL Context and COCO-Stuff datasets. [4] Marius Cordts, Mohamed Omran, Sebastian Ramos, Timo Rehfeld, Markus Enzweiler, Rodrigo Benenson, Uwe Franke, Stefan Roth, and Bernt Schiele. The cityscapes dataset for semantic urban scene understanding. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 3213 3223, 2016. [5] Roozbeh Mottaghi, Xianjie Chen, Xiaobai Liu, Nam-Gyu Cho, Seong-Whan Lee, Sanja Fidler, Raquel Urtasun, and Alan Yuille. The role of context for object detection and semantic segmentation in the wild. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 891 898, 2014. [6] Holger Caesar, Jasper Uijlings, and Vittorio Ferrari. Coco-stuff: Thing and stuff classes in context. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pages 1209 1218, 2018. |
| Dataset Splits | Yes | The Cityscapes dataset contains 2,975 training, 500 validation, and 1,525 testing images... The COCO-Stuff dataset provides 9,000 training and 1,000 validation images... |
| Hardware Specification | Yes | We train the network on 8 TITAN XP. |
| Software Dependencies | No | Only 'Pytorch toolkit' is mentioned without a specific version number. No other software dependencies with version numbers are listed. |
| Experiment Setup | Yes | We use the standard SGD solver with the initial learning rate of 0.001 to train the network. The learning rate is decayed linearly during the training. Each mini-batch contains 8 images. For the Cityscape dataset, we use the image size of 769 769 and 40,000 mini-batches to train the network. For the PASCAL-Context and COCO-Stuff datasets, we set the image to 520 520 and use 60,000 mini-batches. We employ the different scaling factors (i.e., 0.5, 0.75, 1.0, 1.25, 1.5, 1.75) to achieve the multi-scale testing result. |