Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data

Authors: Lan-Zhe Guo, Zhen-Yu Zhang, Yuan Jiang, Yu-Feng Li, Zhi-Hua Zhou

ICML 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental To validate the effectiveness of the proposed method, we conduct experiments on two standard MNIST and CIFAR benchmarks for semi-supervised image classification using deep convolutional neural networks (CNNs).
Researcher Affiliation Academia 1National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China.
Pseudocode Yes Algorithm 1 The DS3L Learning Framework
Open Source Code Yes The code for the work is readily available and freely downloaded at https://www.lamda.nju.edu.cn/code DS3L.ashx.
Open Datasets Yes To validate the effectiveness of the proposed method, we conduct experiments on two standard MNIST and CIFAR benchmarks for semi-supervised image classification using deep convolutional neural networks (CNNs).
Dataset Splits No The paper describes the construction of labeled and unlabeled training data, and refers to a 'test' set, but does not explicitly provide information about a separate 'validation' dataset split or percentage.
Hardware Specification No The paper does not provide specific hardware details such as GPU models, CPU types, or cloud instance specifications used for running experiments.
Software Dependencies No The paper mentions popular deep learning frameworks like Pytorch and Tensorflow but does not specify their version numbers or other ancillary software dependencies with versions.
Experiment Setup Yes The networks are trained using stochastic gradient descent (SGD) methods with a learning rate 1e 3. We train the model for 200,000 updates with a batch size of 100.