Open-world Semi-supervised Novel Class Discovery

Authors: Jiaming Liu, Yangqiming Wang, Tongze Zhang, Yulu Fan, Qinli Yang, Junming Shao

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on three image datasets are conducted and the results show the effectiveness of the proposed method in open-world scenarios, especially with scarce known classes and labels.
Researcher Affiliation Academia University of Electronic Science and Technology of China {liujiaming, leo wang, zhangtongze, ylfan}@std.uestc.edu.cn, {qinli.yang, junmshao}@uestc.edu.cn
Pseudocode No The paper describes the proposed method in text and mathematical equations, but it does not include a dedicated pseudocode or algorithm block.
Open Source Code Yes 1Code and appendix at https://github.com/LiuJMzzZ/OpenNCD
Open Datasets Yes Our proposed approach1 is evaluated on three widely-used datasets in the standard image classification tasks including CIFAR-10 [Krizhevsky, 2009], CIFAR-100 [Krizhevsky, 2009], and Image Net-100, which is randomly sub-sampled with 100 classes from Image Net [Deng et al., 2009] for its large volume.
Dataset Splits No The paper describes how classes are divided into known and unknown, and how labeled data is portioned (e.g., 'only 10% of the known classes are labeled'), but it does not explicitly provide the standard train/validation/test dataset splits (e.g., 80/10/10 split or specific counts) within the text.
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU models, CPU types, memory) used for running the experiments.
Software Dependencies No The paper mentions software components like 'Resnet-18' and 'SimCLR' and an 'Adam optimizer', but it does not specify version numbers for any software libraries or dependencies (e.g., Python, PyTorch, TensorFlow, CUDA, scikit-learn versions).
Experiment Setup Yes 50 prototypes are utilized for the CIFAR-10 dataset and 500 for both the CIFAR-100 and Image Net-100 datasets with a fixed dimension of 32. We adopt an Adam optimizer with a learning rate of 0.002 and fix the batch size to 512 in all experiments. The temperature scale τ is set to 0.1 suggested by most of the previous methods, and the weight of the last two terms in the objective function is set to {λ1, λ2} = {1, 1}. κ is set to 5 in prototype grouping.