Self-Paced Curriculum Learning

Authors: Lu Jiang, Deyu Meng, Qian Zhao, Shiguang Shan, Alexander Hauptmann

AAAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experiments We present experimental results for the proposed SPCL on two tasks: matrix factorization and multimedia event detection. We demonstrate that our approach outperforms baseline methods on both tasks.
Researcher Affiliation Academia 1 School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA, 15217 2 School of Mathematics and Statistics, Xi an Jiaotong University, Xi an, Shaanxi, P. R. China, 710049 3 Institute of Computing Technology, Chinese Academy of Sciences, Beijing, P. R. China, 100190
Pseudocode Yes Algorithm 1: Self-paced Curriculum Learning. input : Input dataset D, predetermined curriculum γ, self-paced function f and a stepsize µ output: Model parameter w 1 Derive the curriculum region Ψ from γ; 2 Initialize v , λ in the curriculum region; 3 while not converged do 4 Update w = arg minw E(w, v ; λ, Ψ); 5 Update v = arg minv E(w , v; λ, Ψ); 6 if λ is small then increase λ by the stepsize µ;
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the proposed methodology.
Open Datasets Yes TRECVID Multimedia Event Detection (MED) 2013 Development, MED13Test and MED14Test sets were used (Over et al. 2013), which include around 34,000 Internet videos.
Dataset Splits Yes all parameters were carefully tuned on a validation set on a different set of events.
Hardware Specification No The paper does not provide specific hardware specifications used for running the experiments.
Software Dependencies No LM-BFGS (Zhu et al. 1997) in stats package in the R language, and Step 4 was solved by a standard quadratic programming toolkit.
Experiment Setup No Mixture scheme was used, and all parameters were carefully tuned on a validation set on a different set of events. ... Step 5 was solved by LM-BFGS (Zhu et al. 1997) in stats package in the R language, and Step 4 was solved by a standard quadratic programming toolkit.