Revisiting Consistency Regularization for Deep Partial Label Learning

Authors: Dong-Dong Wu, Deng-Bao Wang, Min-Ling Zhang

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments on benchmark datasets demonstrate the superiority of the proposed method compared with other state-of-the-art methods. In this section, we conduct experiments on various image datasets showing the effectiveness of our method compared with other state-of-the-art deep PLL methods.
Researcher Affiliation Academia 1School of Computer Science and Engineering, Southeast University, Nanjing 210096, China 2Key Laboratory of Computer Network and Information Integration (Southeast University), Ministry of Education, China. * Correspondence to: Min-Ling Zhang <zhangml@seu.edu.cn>.
Pseudocode Yes Algorithm 1 Our Regularized Training Method
Open Source Code No The paper does not provide an explicit statement about the release of open-source code or a link to a code repository.
Open Datasets Yes We employ five commonly used benchmark image datasets including Kuzushiji-MNIST (Clanuwat et al., 2018), Fashion-MNIST (Xiao et al., 2017), SVHN (Netzer et al., 2011), CIFAR-10 and CIFAR-100 (Krizhevsky et al., 2009).
Dataset Splits No The paper does not explicitly provide specific information about validation dataset splits (e.g., percentages, sample counts, or explicit mention of a validation set).
Hardware Specification Yes Our implementation is based on PyTorch (Paszke et al., 2019), and experiments were carried out with NVIDIA Tesla V100 GPU.
Software Dependencies No The paper mentions 'PyTorch' but does not specify a version number for it or any other software dependency.
Experiment Setup Yes For all methods, we use SGD as the optimizer with a momentum of 0.9, a weight decay of 1e-4 and set batch size to 64. We set total epochs as 200, and the initial learning rate as 0.1 while divided it by 10 after 100 and 150 epochs respectively. For our method, we simply set T = 100, λ = 1 and K = 3 across all datasets.