Trusted Multi-View Deep Learning with Opinion Aggregation
Authors: Wei Liu, Xiaodong Yue, Yufei Chen, Thierry Denoeux7585-7593
AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on various kinds of multi-view datasets verify the reliability and robustness of the proposed multi-view deep learning method. We conduct extensive experiments over various kinds of real-world data to validate the effectiveness of the proposed model in accuracy, reliability and robustness. |
| Researcher Affiliation | Academia | Wei Liu1, Xiaodong Yue1,2 *, Yufei Chen3, Thierry Denoeux4,5 1 School of Computer Engineering and Science, Shanghai University, Shanghai, China 2 Artiļ¬cial Intelligence Institute of Shanghai University, Shanghai, China 3 College of Electronics and Information Engineering, Tongji University, Shanghai, China 4 Universit e de technologie de Compi egne, CNRS UMR 7253 Heudiasyc, Compi egne, France 5 Shanghai University, UTSEUS, Shanghai, China |
| Pseudocode | No | The paper describes the proposed method using textual descriptions and mathematical formulations, but it does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the methodology is openly available. |
| Open Datasets | Yes | We conduct experiments on six real-world multi-view datasets as follows: CUB (Wah et al. 2011): Caltech-UCSD Birds dataset... Food-101 (Wang et al. 2015b): UMPC Food-101 dataset... HMDB (Kuehne et al. 2011): This dataset is one of the largest human action recognition dataset... Handwritten (van Breukelen et al. 1998): This dataset consists of handwritten numerals... Caltech101 (Fei-Fei, Fergus, and Perona 2004): This dataset consists of 8677 images... Scene15 (Fei-Fei and Perona 2005): Scene15 dataset contains 4485 images... |
| Dataset Splits | Yes | We then use 5-fold cross-validation to select the learning rate from 1e 4, 3e 4, 1e 3, 3e 3 . For all datasets, 20% samples are used as test set. |
| Hardware Specification | Yes | The model is implemented by Py Torch on one NVIDIA TITAN Xp with GPU of 12GB memory. |
| Software Dependencies | No | The paper mentions 'Py Torch' and 'Adam optimizer' but does not provide specific version numbers for these software components. For example, it says 'implemented by Py Torch' and 'The Adam optimizer (Kingma and Ba 2014) is used'. |
| Experiment Setup | Yes | For our algorithm, we conduct the fully connected networks for all datasets. The Adam optimizer (Kingma and Ba 2014) is used to train the network, where l2-norm regularization is set to 1e 5. We then use 5-fold cross-validation to select the learning rate from 1e 4, 3e 4, 1e 3, 3e 3 . For all datasets, 20% samples are used as test set. We run 10 times for each method to report the mean values and standard deviations. |