Fusion Label Enhancement for Multi-Label Learning

Authors: Xingyu Zhao, Yuexuan An, Ning Xu, Xin Geng

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on multiple benchmark datasets validate the effectiveness of the proposed approach. In this section, the efficiency and the performance of FLEM are evaluated in multiple MLL datasets.
Researcher Affiliation Academia 1School of Computer Science and Engineering, Southeast University, Nanjing 211189, China 2Key Laboratory of Computer Network and Information Integration (Ministry of Education), Southeast University, Nanjing 211189, China
Pseudocode Yes Algorithm 1 FLEM algorithm
Open Source Code Yes Our code is available at: https://github.com/ailearn-ml/FLEM.
Open Datasets Yes we conduct experiments on several real-world datasets, including AAPD [Yang et al., 2018], Reuters [Debole and Sebastiani, 2005], VOC07, VOC12 [Everingham et al., 2015], COCO14, COCO17 [Lin et al., 2014], CUB [Wah et al., 2011] and NUS [Chua et al., 2009].
Dataset Splits Yes Following common practices [Liu et al., 2017; Lanchantin et al., 2021], these datasets are split into training set, validation set and testing set. Statistics of these real-world datasets are given in Table 1. Ntrain, Nval, Ntest, D, L denote the number of training samples, validation samples, testing samples, feature dimensions and labels respectively.
Hardware Specification Yes All the computations are performed on a GPU server with NVIDIA Tesla V100, Intel Xeon Gold 6240 CPU 2.60 GHz processor and 32 GB GPU memory.
Software Dependencies No The paper mentions 'PyTorch' but does not provide a specific version number. No other software dependencies with version numbers are listed.
Experiment Setup Yes The optimization process spans over 30 epochs using the AMSGrad variant [Reddi et al., 2018] of AdamW [Loshchilov and Hutter, 2017] with a weight decay of 0.0001. The learning rate is set to 0.001 for all algorithms. For FLEM, hyperparameters α and β are are selected by grid search from the set {0.0001, 0.001, 0.01, 0.1}.