Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

Authors: Bo Ye, Kai Gan, Tong Wei, Min-Ling Zhang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on benchmark datasets demonstrate that previous approaches may significantly hinder novel class learning, whereas our method strikingly balances the learning pace between seen and novel classes, achieving a remarkable 3% average accuracy increase on the Image Net dataset.
Researcher Affiliation Academia Bo Ye1,2, Kai Gan1,2, Tong Wei1,2 , Min-Ling Zhang1,2 1School of Computer Science and Engineering, Southeast University, Nanjing 211189, China 2Key Lab. of Computer Network and Information Integration (Southeast University), Mo E, China {yeb, gank, weit, zhangml}@seu.edu.cn
Pseudocode No The paper describes the proposed losses and the final objective function mathematically, but does not provide structured pseudocode or an algorithm block.
Open Source Code Yes Our code is available at https://github.com/yebo0216best/LPS-main.
Open Datasets Yes We evaluate our method on three commonly used datasets, i.e., CIFAR-10, CIFAR-100 [Krizhevsky, 2009], and Image Net [Russakovsky et al., 2015].
Dataset Splits No The paper specifies labeled ratios (10% or 50%) for seen classes but does not explicitly mention the use of a separate validation set or its split percentage/size for hyperparameter tuning or early stopping.
Hardware Specification Yes These experiments are conducted on a single NVIDIA 3090 GPU.
Software Dependencies No The paper mentions using Sim CLR and Rand Augment, and models like ResNet-18/50, but does not provide specific version numbers for software dependencies (e.g., Python, PyTorch, CUDA, or specific library versions).
Experiment Setup Yes For CIFAR-10 and CIFAR-100, we utilize Res Net-18 as our backbone which is trained by the standard SGD with a momentum of 0.9 and a weight decay of 0.0005. We train the model for 200 epochs with a batch size of 512. For the Image Net dataset, we opt for Res Net-50 as our backbone. This choice also undergoes training via the standard SGD, featuring a momentum coefficient of 0.9 and a weight decay of 0.0001. The training process spans 90 epochs, with a batch size of 512. and The cosine annealing learning rate schedule is adopted on CIFAR and Image Net datasets.