STARS: Spatial-Temporal Active Re-sampling for Label-Efficient Learning from Noisy Annotations

Authors: Dayou Yu, Weishi Shi, Qi Yu

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments conducted on both synthetic and real-world data clearly demonstrate the effectiveness of the proposed active re-sampling function.
Researcher Affiliation Academia Dayou Yu1*, Weishi Shi2*, Qi Yu1 1 Rochester Institute of Technology 2University of North Texas {dy2507, qi.yu}@rit.edu, weishi.shi@unt.edu
Pseudocode No The paper describes its methods and algorithms in prose and mathematical formulations but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes Yu, D.; Shi, W. S.; and Yu, Q. 2023. Appendix: STARS: Spatial-Temporal Active Re-Sampling for Label-Efficient Learning from Noisy Annotations. https://github.com/ritmininglab/STARS.git.
Open Datasets Yes We select 5 real-world datasets (Dua and Graff 2017; Shi and Yu 2018) from different domains: medical, bioinformatics, image recognition, and automatic systems. ... Dua, D.; and Graff, C. 2017. UCI Machine Learning Repository. Institution: University of California, Irvine, School of Information and Computer Sciences.
Dataset Splits No The paper mentions using 'annotated dataset' and 'unlabelled dataset' and evaluates performance on real-world datasets but does not explicitly state the specific percentages or counts for training, validation, and test splits used in its experiments.
Hardware Specification No The paper does not provide any specific details about the hardware used to run the experiments, such as GPU models, CPU types, or memory specifications.
Software Dependencies No The paper mentions 'Scikit-learn' in the bibliography as a general machine learning library but does not provide specific version numbers for any software dependencies or libraries used in its experiments.
Experiment Setup Yes For STARS, we linearly increase τ from 0.2 to 0.7 and fix γ to 0.2. ... We use an uncertainty based sampling strategy, Bv SB (Joshi, Porikli, and Papanikolopoulos 2009) for AL to sample new data instances. ... The annotation noise α is set to 0.3.