Group-wise Deep Co-saliency Detection

Authors: Lina Wei, Shanshan Zhao, Omar El Farouk Bourahla, Xi Li, Fei Wu

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate the effectiveness of our approach in comparison with the state-of-the-art approaches.
Researcher Affiliation Academia Lina Wei1, Shanshan Zhao1, Omar El Farouk Bourahla1, Xi Li1,2, , Fei Wu1 1 Zhejiang University, Hangzhou, China 2 Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China
Pseudocode No The paper describes the network architecture and processes with text and diagrams but does not include explicit pseudocode or algorithm blocks.
Open Source Code No The paper does not provide an explicit statement or link for the open-source code of the described methodology.
Open Datasets Yes We conduct a set of qualitative and quantitative experiments on three benchmark datasets annotated with pixel-wised ground-truth labeling, including the i Coseg dataset [Batra et al., 2010], the MSRC-v2 dataset [Winn et al., 2005] and the Cosal2015 dataset [Zhang et al., 2016b]. The training data we used in our approach are generated from existing image dataset(Coco dataset [Lin et al., 2014]) which has 9213 images with the masks information.
Dataset Splits No The paper mentions training data and test data, but it does not explicitly specify a validation dataset split for hyperparameter tuning or early stopping during training.
Hardware Specification No The paper does not explicitly provide specific hardware details such as GPU models, CPU models, or memory used for running the experiments.
Software Dependencies No The paper mentions that 'The fully convolutional network (FCN) is implemented by using the Caffe [Jia et al., 2014] toolbox' and uses 'VGG 16-layer net [Simonyan and Zisserman, 2014]', but it does not specify version numbers for Caffe or any other software dependencies.
Experiment Setup Yes We resize all the images and ground-truth maps to 128 256 pixels for training. The momentum parameter is chosen as 0.99, the learning rate is set to 1e-10, and the weight decay is 0.0005. We need about 60000 training iterations for convergence.