Cross-Modal Subspace Clustering via Deep Canonical Correlation Analysis

Authors: Quanxue Gao, Huanhuan Lian, Qianqian Wang, Gan Sun3938-3945

AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on several real-world datasets demonstrate the proposed method outperforms the state-of-the-art methods.
Researcher Affiliation Academia 1State Key Laboratory of Integrated Services Networks, Xidian University, Xi an 710071, China. 2State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences, China.
Pseudocode Yes Algorithm 1 CMSC-DCCA
Open Source Code No The paper does not provide any explicit statement or link for open-source code availability for the described methodology.
Open Datasets Yes Datasets Settings: The used datasets in our experiments include: 1) FRGC Dataset (Yang, Parikh, and Batra 2016); 2) Fashion-MNIST Dataset (Xiao, Rasul, and Vollgraf 2017); 3) YTF Dataset (Wolf, Hassner, and Maoz 2011); 4) COIL-20 Dataset
Dataset Splits No The paper mentions 'train' steps but does not provide specific details on dataset splits (e.g., percentages or exact sample counts) for training, validation, or test sets.
Hardware Specification Yes NVIDIA Titan Xp Graphics Processing Units (GPUs) and 64 GB memory size.
Software Dependencies No The paper mentions 'Py Torch' but does not specify its version number or any other software dependencies with version information.
Experiment Setup Yes Implementation details: In our model, we use the four-layer encoders including three convolution encoding layers and a fully connected layer, and the corresponding decoders consist of a fully connected layer and three deconvolution decoding layers. More specific settings are given in Table 1. ... We set the learning-rate to 0.001. ... We set 10000 epochs to train the entire network