Densely Cascaded Shadow Detection Network via Deeply Supervised Parallel Fusion

Authors: Yupei Wang, Xin Zhao, Yin Li, Xuecai Hu, Kaiqi Huang

IJCAI 2018 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our method is evaluated on two widely used shadow detection benchmarks. Experimental results show that our method outperforms state-of-the-arts by a large margin.
Researcher Affiliation Academia 1 CRIPAC, NLPR, Institute of Automation, Chinese Academy of Sciences 2 University of Chinese Academy of Sciences 3 Carnegie Mellon University 4 University of Science and Technology of China 5 CAS Center for Excellence in Brain Science and Intelligence Technology
Pseudocode No The paper describes the model architecture and processes using text and diagrams, but does not include any structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any explicit statements about releasing source code for the described methodology, nor does it include links to a code repository.
Open Datasets Yes We evaluate our method on two widely used benchmarks: SBU [Vicente et al., 2016] and UCF [Zhu et al., 2011].
Dataset Splits No The paper states 'we train our models on SBU training set, and evaluate the trained models on SBU testing set and UCF testing set,' but does not explicitly mention a separate validation set or provide details on its split.
Hardware Specification No The paper does not provide specific details about the hardware used for running the experiments, such as GPU or CPU models.
Software Dependencies No The paper states 'All our models are trained using Caffe [Jia et al., 2014] as backend,' but does not provide specific version numbers for Caffe or any other software dependencies.
Experiment Setup Yes The hyperparameters, including the initial learning rate, weight decay and momentum, are set to 1e-8, 2e-4 and 0.9, respectively. Our DSPF network is initialized from the trained HED network. And our DC-DSPF is further trained on top of DSPF. The hyper-parameters of DC-DSPF are set to 1e-8, 2e-4 and 0.99 respectively for the initial learning rate, weight decay and momentum. All new convolutional layers are initialized with Gaussian random distribution with fixed mean (0.0) and variance(0.01). We apply random flipping for data augmentation during training.