Self-Paced Boost Learning for Classification

Authors: Te Pi, Xi Li, Zhongfei Zhang, Deyu Meng, Fei Wu, Jun Xiao, Yueting Zhuang

IJCAI 2016 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The experiments on several real-world datasets show the superiority of SPBL in terms of both effectiveness and robustness.
Researcher Affiliation Academia 1Zhejiang University, Hangzhou, China; 2Xi an Jiaotong University, Xi an, China
Pseudocode Yes Algorithm 1: SPBL for Classification
Open Source Code No The paper does not provide any explicit statement or link for open-source code for the described methodology.
Open Datasets Yes Three real-world image datasets are used. We choose the image data for experiments because the underlying patterns of image features tend to have rich nonlinear correlations. The three datasets are Caltech2561, Animal With Attributes (AWA)2, Corel10k3. All of them are publicly available and fully labeled with each sample belonging to only one class.
Dataset Splits Yes Caltech256 SP 256 29780 (50%/20%/30%) AWA Decaf 50 30475 (50%/20%/30%) Corel10k SP 100 10000 (50%/20%/30%)
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments.
Software Dependencies No The paper mentions features (spatial pyramid features, Decaf feature) and general techniques (logistic linear form for h(x)), but does not provide specific software names with version numbers.
Experiment Setup Yes We implement a grid search for the tuning of the hyperparameter. Further, in order to test the robustness of our model, we manually add label noise into the training set by randomly selecting and relabeling s% of the training samples with the other labels different from the true ones. We conduct experiments with s 2 {0, 5, 10, 15} for the three datasets. We adopt the strategy in [Jiang et al., 2014b] for the annealing of the SPL parameters (λ, ) (Line 10 to 12 in Algorithm 1). Specifically, at each iteration, we sort the samples in the ascending order of their losses, and set (λ, ) based on the number of samples to be selected by now.