SOGNet: Scene Overlap Graph Network for Panoptic Segmentation
Authors: Yibo Yang, Hongyang Li, Xia Li, Qijie Zhao, Jianlong Wu, Zhouchen Lin12637-12644
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on COCO and Cityscapes demonstrate that our method is able to accurately predict overlap relations, and outperform the state-of-the-art performance for panoptic segmentation. We conduct experiments on the COCO and Cityscapes datasets for panoptic segmentation, and show that our proposed SOGNet is able to accurately predict overlap relations and outperform state-of-the-art performances. |
| Researcher Affiliation | Collaboration | Yibo Yang,1,2, Hongyang Li,2, Xia Li,2,3 Qijie Zhao,4 Jianlong Wu,2,5 Zhouchen Lin2, 1Center for Data Science, Academy for Advanced Interdisciplinary Studies, Peking University 2Key Laboratory of Machine Perception (MOE), School of EECS, Peking University 3Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University 4Pony.ai Inc 5School of Computer Science and Technology, Shandong University |
| Pseudocode | No | The paper describes its methodology in prose and mathematical equations but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement or a link to its own open-source code for the described methodology. |
| Open Datasets | Yes | Experiments on COCO and Cityscapes demonstrate that our method is able to accurately predict overlap relations, and outperform the state-of-the-art performance for panoptic segmentation. We conduct experiments on the COCO and Cityscapes datasets for panoptic segmentation. |
| Dataset Splits | Yes | Our reported OA is an average over all images in the validation set. On the COCO validation set, SOGNet has a 1.2% improvement than UPSNet using the same backbone. We run SOGNet on the COCO and Cityscapes datasets, and compare the results with state-of-the-art methods...Our proposed SOGNet achieves the highest single-model performance on the COCO test-dev set. |
| Hardware Specification | No | The paper mentions training with 'a batchsize of 8 images distributed on 8 GPUs' but does not specify the exact GPU models, CPU models, or any other detailed hardware specifications. |
| Software Dependencies | No | The paper mentions components like 'Res Net with FPN', 'Mask R-CNN', and 'SGD optimizer', but does not provide specific version numbers for any software libraries, frameworks, or programming languages used. |
| Experiment Setup | Yes | We set the weights of loss functions following (Xiong et al. 2019). The weight of panoptic head is 0.1 for COCO and 0.5 for Cityscapes. The weight of relation loss is set to 1.0. We train the models with a batchsize of 8 images distributed on 8 GPUs. The SGD optimizer with 0.9 Nesterov momentum and a weight decay of 10 4 is used. We use an equivalent setting to UPSNet for fair comparison. Images are resized with the shorter edge as 800, and the longer edge less than 1333. We freeze all batch normalization (BN) (Ioffe and Szegedy 2015) layers within the Res Net backbone. For COCO, we train the SOGNet for 180K iterations. The initial learning rate is set to 0.01 and is divided by 10 at the 120K-th and 160K-th iterations. For Cityscapes, we train for 24K iterations and drop the learning rate at the 18K-th iteration. |