Salient Object Detection by Lossless Feature Reflection

Authors: Pingping Zhang, Wei Liu, Huchuan Lu, Chunhua Shen

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

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experiments on seven saliency detection datasets demonstrate that our approach achieves consistently superior performance and outperforms the very recent state-of-the-art methods.
Researcher Affiliation Academia 1 Dalian University of Technology, Dalian, 116024, P.R. China 2 Shanghai Jiao Tong University, Shanghai, 200240, P.R. China 3 University of Adelaide, Adelaide, SA 5005, Australia
Pseudocode No The paper does not contain any structured pseudocode or algorithm blocks.
Open Source Code Yes The source code is publicly available at http://ice.dlut.edu.cn/lu/.
Open Datasets Yes To train our model, we adopt the MSRA10K [Borji et al., 2015] dataset, which has 10,000 training images with high quality pixel-wise saliency annotations.
Dataset Splits No We do not use validation set and train the model until its training loss converges.
Hardware Specification Yes We train and test our method with an NVIDIA Titan 1070 GPU (8G memory) and an i5-6600 CPU.
Software Dependencies No The paper states: 'We implement our model based on the Caffe toolbox [Jia et al., 2014] with the MATLAB 2016 platform.' While MATLAB 2016 specifies a version, Caffe is not given a specific version number, only a citation.
Experiment Setup Yes The input image is uniformly resized into 384 384 3 pixels and subtracted the Image Net mean [Deng et al., 2009]... During the training, we use standard SGD method with batch size 12, momentum 0.9 and weight decay 0.0005. We set the base learning rate to 1e-8 and decrease the learning rate by 10% when training loss reaches a flat. The training process converges after 150k iterations.