DP-SSL: Towards Robust Semi-supervised Learning with A Few Labeled Samples

Authors: Yi Xu, Jiandong Ding, Lu Zhang, Shuigeng Zhou

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on four standard SSL benchmarks show that DP-SSL can provide reliable labels for unlabeled data and achieve better classification performance on test sets than existing SSL methods, especially when only a small number of labeled samples are available. Concretely, for CIFAR-10 with only 40 labeled samples, DP-SSL achieves 93.82% annotation accuracy on unlabeled data and 93.46% classification accuracy on test data, which are higher than the SOTA results.
Researcher Affiliation Collaboration Yi Xu1 Jiandong Ding2 Lu Zhang1 Shuigeng Zhou 1 1Shanghai Key Lab of Intelligent Information Processing, and School of Computer Science, Fudan University, China 2Alibaba Group
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not include any explicit statement or link indicating that the authors are releasing the source code for their method.
Open Datasets Yes We compare DP-SSL with major existing methods on CIFAR-10 [53], CIFAR-100 [53], SVHN [54] and STL-10 [55].
Dataset Splits Yes CIFAR-10 and CIFAR-100 [53] contain 50,000 training examples and 10,000 validation examples. SVHN [54] is a digital image dataset that consists of 73,257, 26,032 and 531,131 samples in the train, test, and extra folders. STL-10 [55]...consists of 5000 labeled images and 8000 validation samples of 96x96 size from 10 classes.
Hardware Specification Yes All experiments are implemented in Pytorch v1.7 and conducted on 16 NVIDIA RTX3090s.
Software Dependencies Yes All experiments are implemented in Pytorch v1.7 and conducted on 16 NVIDIA RTX3090s.
Experiment Setup Yes In our framework, the batch size for labeled data and unlabeled data is set to 64 and 448, respectively. Besides, we use the same hyperparameters (K = 50, ρ = 0.2, ϵ = 0.95) for all datasets.