Deep Salience: Visual Salience Modeling via Deep Belief Propagation

Authors: Richard Jiang, Danny Crookes

AAAI 2014 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental evaluation on the benchmark dataset validated that our Deep Salience model can consistently outperform eleven state-of-the-art salience models, yielding the higher rates in the precision-recall tests and attaining the best F-measure and mean-square error in the experiments.
Researcher Affiliation Academia Richard Jiang Automatic Control and System Engineering The University of Sheffield Sheffield, United Kingdom E-mail: richardjiang@acm.org Danny Crookes ECIT Institute Queen s University Belfast Belfast, United Kingdom E-mail: d.crookes@qub.ac.uk
Pseudocode No The paper does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described.
Open Datasets Yes We tested our method on the widely used object dataset --the EPFL object dataset (Achanta et al 2009), which is publicly available and the ground truth of foreground objects is provided as binary masks.
Dataset Splits No The paper mentions using the EPFL dataset but does not provide specific details on training, validation, and test splits needed to reproduce the data partitioning. It only states that 'The curves are computed in the same way as reported by previous work.'
Hardware Specification No The paper mentions that 'The computing time was measured for a MATLAB solution.' but does not provide specific hardware details (e.g., CPU, GPU models, memory) used for running its experiments.
Software Dependencies No The paper states 'Our algorithm was implemented in MATLAB.' but does not provide specific version numbers for MATLAB or any other ancillary software dependencies.
Experiment Setup No The paper mentions some setup details such as using the SF method for initialization and assuming border pixels as background, but it does not provide specific experimental setup details like concrete hyperparameter values, training configurations, or system-level settings.