Locally Normalized Soft Contrastive Clustering for Compact Clusters
Authors: Xin Ma, Won Hwa Kim
IJCAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experimental results on various datasets illustrate that our proposed approach achieves outstanding clustering performance over most of the state-of-the-art clustering methods for both image and non-image data even without convolution. and we carry extensive empirical validation of LNSCC with various independent datasets, demonstrating competitive qualitative and quantitative performances. |
| Researcher Affiliation | Academia | 1Computer Science and Engineering, University of Texas at Arlington, USA 2Computer Science and Engineering, POSTECH, South Korea 3Graduate School of AI, POSTECH, South Korea |
| Pseudocode | No | The paper describes its method using textual descriptions and mathematical equations but does not include a structured pseudocode block or algorithm box. |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | Yes | To evaluate performances of different clustering methods, five popular public datasets were used: REUTERS-10K [Guo et al., 2017], MNIST, MNIST-test, USPS, and Fashion-MNIST. |
| Dataset Splits | Yes | The experimental settings follow [Van Gansbeke et al., 2020] for SCAN which trains and evaluates the model using the train and validation splits, respectively. |
| Hardware Specification | No | The paper does not explicitly provide details about the specific hardware (e.g., GPU or CPU models) used for running the experiments. |
| Software Dependencies | No | The paper mentions using 'MLP', 'SGD as the optimizer', and 'Pretrained VGG', but it does not specify versions for programming languages, libraries, or frameworks (e.g., Python version, PyTorch/TensorFlow versions). |
| Experiment Setup | Yes | The input data were projected onto a low-dimensional space with an MLP (with layers: 500, 500, 2000 nodes) which is widely used in other DC methods, while the clustering head is also implemented using an MLP (with one layer: 32 nodes). The dimension of Z was set to 64. When constructing the locally normalized k NN graph Glg, the number of nearest neighbors was set to 10 and 70 only for REUTERS-10k dataset, and Euclidean distance was used for distance metric. For the MLPs, we used Stochastic Gradient Descent (SGD) as the optimizer with learning rate 0.01, momentum 0.9, and weight decay 0.0005 and the batch size was set to 200. The α in (6) was 2, the β in (16) was 5, the γ in (18) was 1, and the (δ, ξ) were set as (0.05, 5) in (19). |