Deep Plug-and-Play Clustering with Unknown Number of Clusters
Authors: An Xiao, Hanting Chen, Tianyu Guo, QINGHUA ZHANG, Yunhe Wang
TMLR 2023 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Experiments on benchmark datasets demonstrate that the proposed method can achieve comparable performance with the state-of-the-art works without requiring the number of clusters. We conduct experimental evaluation on the CIFAR-10 (Krizhevsky et al., 2009), CIFAR100-20 (Krizhevsky et al., 2009), STL-10 (Coates et al., 2011), Image Net-10 (Deng et al., 2009) and Image Net-50 (Deng et al., 2009) datasets. We train and evaluate these datasets using their train and validation split to study the generalization properties of the proposed method. To evaluate the clustering performance of various methods, we adopt three standard evaluation metrics: Clustering Accuracy (ACC), Normalized Mutual Information (NMI) and Adjusted Rand Index (ARI). |
| Researcher Affiliation | Industry | An Xiao EMAIL Huawei Noah s Ark Lab Hanting Chen EMAIL Huawei Noah s Ark Lab Tianyu Guo EMAIL Huawei Noah s Ark Lab Qinghua Zhang EMAIL Huawei Noah s Ark Lab Yunhe Wang EMAIL Huawei Noah s Ark Lab |
| Pseudocode | Yes | Algorithm 1 Deep plug-and-play clustering with unknown number of clusters. Require: A parametric clustering algorithm A, an initial number of clusters K , the split and merge hyperparameter λ, and the dataset X to be clustered. |
| Open Source Code | No | The paper does not contain an explicit statement about releasing source code for the described methodology, nor does it provide a direct link to a code repository. |
| Open Datasets | Yes | We conduct experimental evaluation on the CIFAR-10 (Krizhevsky et al., 2009), CIFAR100-20 (Krizhevsky et al., 2009), STL-10 (Coates et al., 2011), Image Net-10 (Deng et al., 2009) and Image Net-50 (Deng et al., 2009) datasets. |
| Dataset Splits | Yes | We conduct experimental evaluation on the CIFAR-10 (Krizhevsky et al., 2009), CIFAR100-20 (Krizhevsky et al., 2009), STL-10 (Coates et al., 2011), Image Net-10 (Deng et al., 2009) and Image Net-50 (Deng et al., 2009) datasets. We train and evaluate these datasets using their train and validation split to study the generalization properties of the proposed method. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory amounts) used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific ancillary software details (e.g., library or solver names with version numbers) needed to replicate the experiment. |
| Experiment Setup | Yes | Training details. We apply the proposed plug-and-play module in the deep clustering method SCAN (Van Gansbeke et al., 2020) without changing their original training settings, including the learning rate, weight decay, neural network architecture, data pre-processing and augmentation. For the proposed method, the hyper-parameters λ is set as 2.0. |