Hypergraph Induced Convolutional Manifold Networks

Authors: Taisong Jin, Liujuan Cao, Baochang Zhang, Xiaoshuai Sun, Cheng Deng, Rongrong Ji

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on the image classification task on large benchmarking datasets demonstrate that our model achieves much better performance than the state-of-the-art.
Researcher Affiliation Academia 1Fujian Key Laboratory of Sensing and Computing for Smart City, School of Information Science and Engineering, Xiamen University, 361005, China 2 Science and Technology on Electro-Optical Control Laboratory, Luoyang, 471023, China 3School of Automation Science and Electrical Engineering, Beihang University, 100083, China 4School of Electronic Engineering, Xidian University, 710071, China
Pseudocode Yes Algorithm 1 Training of convolutional manifold networks
Open Source Code No The paper does not contain any explicit statement that the authors are releasing their code or provide a link to a code repository for the methodology described.
Open Datasets Yes We conducted the classification experiments on the CIFAR-10 natural image dataset [Krizhevsky, 2009]; In our experiments, the SVHN digit dataset [Netzer et al., 2012] and CIFAR-10 and CIFAR-100 natural image datasets [Krizhevsky, 2009] are added to Gaussian noise for classification tasks.; Finally, we conducted the classification experiments on the Large-scale Image Net dataset.
Dataset Splits No The paper mentions training and testing but does not explicitly provide specific details about a validation dataset split (e.g., percentages, sample counts, or methodology).
Hardware Specification Yes The compared deep learning models were trained on the 4 GPUs (Titan XP), which have 3.20G HZ and 12G memory.
Software Dependencies No The paper mentions deep learning frameworks and models used (e.g., VGG, Google Net), but does not specify software versions for libraries, frameworks, or programming languages (e.g., Python version, TensorFlow/PyTorch version, CUDA version).
Experiment Setup Yes the feature buffer size is set to 100 and the neighborhood size parameter is set to 10. The mini-batch size is set to 150. The number of the epochs for our model is set to be 180. Our model has four essential parameters: (1) the ℓ2-norm regularization parameter λ of ridge regression, (2) the trade-off parameter ρ between the softmax loss and the manifold loss, (3) the weight decay coefficient γ, and (4) the threshold parameter τ of the hyperedge generation. For the threshold parameter τ, we set the threshold parameter as the function of the largest coefficient of centroid sample, i.e., τ = τ s(cmax), where cmax is the largest coefficient of the centroid sample. In addition, (1) the size of feature buffer k0 and (2) the neighborhood size k are also two issues that affect the performance.