Learning Context-Aware Classifier for Semantic Segmentation
Authors: Zhuotao Tian, Jiequan Cui, Li Jiang, Xiaojuan Qi, Xin Lai, Yixin Chen, Shu Liu, Jiaya Jia
AAAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | The implementation is available at https://github.com/tianzhuotao/CAC.We adopt two challenging semantic segmentation benchmarks (ADE20K (Zhou et al. 2017) and COCO-Stuff 164K (Caesar, Uijlings, and Ferrari 2016)) in this paper. Models are trained and evaluated on the training and validation sets of these datasets respectively.Table 1: Performance Comparison on ADE20K (Zhou et al. 2017) and COCO-Stuff 164K (Caesar, Uijlings, and Ferrari 2016). Single-scale (s.s.) and multi-scale (m.s.) evaluation results are reported, and values of fps (frames per second) are obtained with resolution 512 512 on a single NVIDIA RTX 2080Ti GPU. |
| Researcher Affiliation | Collaboration | Zhuotao Tian1,4, Jiequan Cui1, Li Jiang2, Xiaojuan Qi3, Xin Lai1 Yixin Chen1, Shu Liu4, Jiaya Jia1,4 1The Chinese University of Hong Kong 2Max Planck Institute for Informatics 3The University of Hong Kong 4Smart More Corporation |
| Pseudocode | No | The paper describes its method using textual descriptions and mathematical equations (e.g., Eq. 1 to Eq. 11) but does not include any explicitly labeled pseudocode or algorithm blocks. |
| Open Source Code | Yes | The implementation is available at https://github.com/tianzhuotao/CAC. |
| Open Datasets | Yes | We adopt two challenging semantic segmentation benchmarks (ADE20K (Zhou et al. 2017) and COCO-Stuff 164K (Caesar, Uijlings, and Ferrari 2016)) in this paper. |
| Dataset Splits | Yes | Models are trained and evaluated on the training and validation sets of these datasets respectively. |
| Hardware Specification | Yes | values of fps (frames per second) are obtained with resolution 512 512 on a single NVIDIA RTX 2080Ti GPU. |
| Software Dependencies | No | Implementations regarding baseline models and benchmarks are based on the default configurations of MMSegmentation (Contributors 2020), and they are kept intact when implemented with our method. The paper mentions MMSegmentation but does not provide a specific version number for it or any other software dependencies. |
| Experiment Setup | Yes | The projectors θy and θp are both composed of two linear layers ([2d d/2] [d/2 d], d = 512) with an intermediate Re LU layer. The loss weight λKL and the scaling factor τ for cosine similarity are empirically set to 1 and 15, and they work well in our experiments. |