CFDM: Contrastive Fusion and Disambiguation for Multi-View Partial-Label Learning

Authors: Qiuru Hai, Yongjian Deng, Yuena Lin, Zheng Li, Zhen Yang, Gengyu Lyu

AAAI 2025 | Venue PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on multiple datasets have demonstrated that our proposed method is superior to other state-of-the-art methods. Experimental Settings Datasets. To evaluate the performance of our proposed CFDM, we conducted experiments on six synthetic MVPLL datasets
Researcher Affiliation Collaboration 1College of Computer Science, Beijing University of Technology 2Idealism Beijing Technology Co., Ltd.
Pseudocode Yes Algorithm 1: Pseudo-code of CFDM (one epoch)
Open Source Code No The paper does not provide any explicit statements about code availability, nor does it include links to a code repository or mention code in supplementary materials.
Open Datasets Yes To evaluate the performance of our proposed CFDM, we conducted experiments on six synthetic MVPLL datasets, which are generated from the widely-used multi-view datasets, including MSRCv1 (Xu, Han, and Nie 2016), Caltech101-7 (Fei-Fei, Fergus, and Perona 2004), Mfeat (Wang, Yang, and Liu 2019), Scence15 (Fei-Fei and Perona 2005), CCV (Jiang et al. 2011), Caltech101-all (Fei Fei, Fergus, and Perona 2004)
Dataset Splits Yes For all experiments, we utilize 5-fold cross-validation, and record the mean and standard deviation (mean std) as the final results.
Hardware Specification Yes All experiments are conducted on a machine equipped with an Intel(R) Xeon(R) Gold 6148 2.40GHz CPU, Ge Force RTX 3090 GPU, and 512GB RAM.
Software Dependencies No The paper mentions using Pytorch (Paszke et al. 2019) and the Adam optimizer but does not specify version numbers for PyTorch or any other libraries or software components.
Experiment Setup Yes The learning rate is chosen from {1e 4, 3e 4, 5e 4}. The hyperparameter γ is set to 0.99, τ is set to 0.07, while β linearly decreases from 0.95 to 0.8. The number of training epochs is set to 130.