Gated Fully Fusion for Semantic Segmentation
Authors: Xiangtai Li, Houlong Zhao, Lei Han, Yunhai Tong, Shaohua Tan, Kuiyuan Yang11418-11425
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We achieve the state of the art results on four challenging scene parsing datasets including Cityscapes, Pascal Context, COCO-stuff and ADE20K. The proposed method is extensively verified on four standard semantic segmentation benchmarks including Cityscapes, Pascal Context, COCO-stuff and ADE20K, where our method achieves state-of-the-art performance on all four tasks. |
| Researcher Affiliation | Collaboration | Xiangtai Li,1 Houlong Zhao,2 Lei Han,3 Yunhai Tong,1 Shaohua Tan,1 Kuiyuan Yang2 1School of EECS, Peking University 2Deep Motion 3Tecent AI Lab {lxtpku, yhtong}@pku.edu.cn, tan@cis.pku.edu.cn {houlongzhao, kuiyuanyang}@deepmotion.ai leihan.cs@gmail.com |
| Pseudocode | No | The paper does not contain structured pseudocode or algorithm blocks clearly labeled as 'Pseudocode' or 'Algorithm'. |
| Open Source Code | No | The paper does not provide a direct link to source code or explicitly state that the code for the described methodology is publicly available. |
| Open Datasets | Yes | We achieve the state of the art results on four challenging scene parsing datasets including Cityscapes, Pascal Context, COCO-stuff and ADE20K. Cityscapes (Cordts et al. 2016), Pascal Context (Mottaghi et al. 2014), COCO Stuff (Caesar, Uijlings, and Ferrari 2018), Microsoft COCO dataset (Lin et al. 2014). |
| Dataset Splits | Yes | For Cityscapes, crop size of 864 864 is used, 100K training iterations with mini-batch size of 8 is carried for training. Cityscapes is a large-scale dataset for semantic urban scene understanding. It contains 5000 fine pixel-level annotated images, which is divided into 2975, 500, and 1525 images for training, validation and testing respectively, where labels of training and validation are publicly released and labels of testing set are held for online evaluation. For ADE20K, COCO-stuff and Pascal Context, crop size of 512 512 is used (images with side smaller than the crop size are padded with zeros), 150K training iterations are used with mini-batch size of 16. ADE20K...contains 20K/2K images for training and validation. Pascal Context...4998 training images and 5105 testing images. COCO Stuff...9000 images are for training and 1000 images for testing. |
| Hardware Specification | No | The paper does not specify the exact hardware components (e.g., GPU models, CPU models, specific cloud instances) used for running the experiments. |
| Software Dependencies | No | Our implementation is based on Py Torch (Paszke et al. 2017). The paper mentions PyTorch but does not provide a specific version number, nor does it list other software dependencies with version numbers. |
| Experiment Setup | Yes | The weight decay is set to 1e-4. Standard SGD is used for optimization, and poly learning rate scheduling policy is used to adjust learning rate, where initial learning rate is set to 1e-3 and decayed by (1 iter total iter)power with power = 0.9. Synchronized batch normalization (Zhang et al. 2018a) is used. For Cityscapes, crop size of 864 864 is used, 100K training iterations with mini-batch size of 8 is carried for training. For ADE20K, COCO-stuff and Pascal Context, crop size of 512 512 is used (images with side smaller than the crop size are padded with zeros), 150K training iterations are used with mini-batch size of 16. As a common practice to avoid , data augmentation including random horizontal flipping, random cropping, random color jittering within the range of [ 10, 10], and random scaling in the range of [0.75, 2] are used during training. |