Region Mutual Information Loss for Semantic Segmentation

Authors: Shuai Zhao, Yang Wang, Zheng Yang, Deng Cai

NeurIPS 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate that RMI can achieve substantial and consistent improvements in performance on PASCAL VOC 2012 and Cam Vid datasets.
Researcher Affiliation Collaboration 1State Key Lab of CAD&CG, College of Computer Science, Zhejiang University 2School of Artificial Intelligence and Automation, Huazhong University of Science and Technology 3Fabu Inc., Hangzhou, China 4Alibaba-Zhejiang University Joint Institute of Frontier Technologies
Pseudocode No The paper describes the methodology mathematically but does not include any pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https://github.com/ZJULearning/RMI.
Open Datasets Yes We evaluate our method on two dataset, PASCAL VOC 2012 [10] and Cam Vid [4] datasets.
Dataset Splits Yes PASCAL VOC 2012 dataset contains 1 464 (train), 1 449 (val), and 1 456 (test) images.
Hardware Specification No The paper mentions 'GPU memory' but does not provide specific hardware details such as GPU model, CPU, or memory amounts used for experiments.
Software Dependencies No The paper mentions 'Py Torch [26] and Tensorflow [1]' as supported platforms but does not provide specific version numbers for these or other software dependencies.
Experiment Setup Yes For PASCAL VOC 2012 dataset, the model is trained on the trainaug [13] set which contains 10 582 images, max_iter is about 30K, lr = 0.007, and slow_iters = 1.5K. For Cam Vid dataset, we train the model on the train and validation sets, max_iter is about 6K, lr = 0.025, and slow_iters = 300. During training, the batch size is always 16. The crop size is 513 and 479 for PASCAL VOC 2012 and Cam Vid datasets respectively.