Efficient Mirror Detection via Multi-Level Heterogeneous Learning

Authors: Ruozhen He, Jiaying Lin, Rynson W.H. Lau

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

Reproducibility Variable Result LLM Response
Research Type Experimental Compared to the state-of-the-art method, Het Net runs 664% faster and draws an average performance gain of 8.9% on MAE, 3.1% on Io U, and 2.0% on F-measure on two mirror detection benchmarks. We conduct experiments on two datasets: MSD (Yang et al. 2019) and PMD (Lin, Wang, and Lau 2020).
Researcher Affiliation Academia Department of Computer Science, City University of Hong Kong ruozhenhe2-c@my.cityu.edu.hk, jiayinlin5-c@my.cityu.edu.hk, rynson.lau@cityu.edu.hk
Pseudocode No The paper describes its method in text and with mathematical formulas, but does not include any explicitly labeled pseudocode or algorithm blocks.
Open Source Code Yes The code is available at https://github.com/Catherine-R-He/Het Net.
Open Datasets Yes We conduct experiments on two datasets: MSD (Yang et al. 2019) and PMD (Lin, Wang, and Lau 2020).
Dataset Splits No The paper specifies training and testing sets for the datasets but does not explicitly detail a validation set split or methodology for it.
Hardware Specification Yes We implement our model by Py Torch and conduct experiments on a Ge Force RTX2080Ti GPU.
Software Dependencies No The paper states 'We implement our model by Py Torch' but does not provide specific version numbers for PyTorch or any other software dependencies.
Experiment Setup Yes We use the stochastic gradient descent (SGD) optimizer with a momentum value of 0.9 and a weight decay of 5e-4. In the training phase, the maximum learning rate is 1e-2, the batch size is 12, and the training epoch is 150.