Uncertainty-Aware Multi-View Representation Learning

Authors: Yu Geng, Zongbo Han, Changqing Zhang, Qinghua Hu7545-7553

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our model achieves superior performance in extensive experiments and shows the robustness to noisy data.
Researcher Affiliation Academia College of Intelligence and Computing, Tianjin University, Tianjin, China 2 Tianjin Key Lab of Machine Learning, Tianjin, China
Pseudocode No The paper describes the proposed model and learning process in text and with figures, but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not contain an explicit statement about releasing the source code for the proposed methodology, nor does it provide a link to a code repository.
Open Datasets Yes We conduct experiments on six real-world multi-view datasets as follows: UCI-MF (UCI Multiple Features)1: This dataset consists of handwritten numerals ( 0 9 ) from a collection of Dutch utility maps. These digits are represented with six types of features. 1https://archive.ics.uci.edu/ml/datasets/Multiple+Features ORL2: ORL face dataset contains 10 different images of each of 40 distinct subjects under different conditions. Three types of features: intensity, LBP and Gabor are used as different views. 2http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html COIL20MV3: There are 1440 images from 20 object categories. Three types of features that are same to ORL are used. 3http://www.cs.columbia.edu/CAVE/software/softlib/ MSRCV1 (Xu, Han, and Nie 2016): This dataset contains 30 different images for each class out of 7 classes in total. Six types of features: CENT, CMT, GIST, HOG, LBP, SIFT are extracted. CUB4: Caltech-UCSD Birds dataset contains 200 different bird categories with 11788 images and text descriptions. Features of 10 categories are extracted by Goog Le Net and Doc2Vec in Gensim5. 4http://www.vision.caltech.edu/visipedia/CUB-200.html Caltech1016: This dataset contains images of 101 object categories. About 40 to 800 images per category. We use a subset of 1,474 images with 6 views. 6http://www.vision.caltech.edu/Image Datasets/Caltech101
Dataset Splits No The paper states 'We divide the learned representations into training and testing sets with different proportions, denoted as Gratio/Pratio, where G is gallery set and P is probe set' but does not explicitly mention a separate validation split.
Hardware Specification Yes The model is implemented by Py Torch on one NVIDIA Geforce GTX TITAN Xp with GPU of 12GB memory.
Software Dependencies No The paper mentions 'Py Torch' as the implementation framework but does not specify its version number or versions of other software dependencies.
Experiment Setup Yes For all datasets, 3-layer fully connected network followed by Re LU activation function is used in the experiments. The latent representation hi is randomly initialized with Gaussian distribution. Adam optimizer (Kingma and Ba 2014) is employed for optimization of all parameters. The dimensions are selected from [10, 20, 50, 100, 200].