Detecting Robust Co-Saliency with Recurrent Co-Attention Neural Network

Authors: Bo Li, Zhengxing Sun, Lv Tang, Yunhan Sun, Jinlong Shi

IJCAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Extensive experimental results demonstrate the superiority of our approach in comparison with the state-of-the-art methods.
Researcher Affiliation Academia 1State Key Lab for Novel Software Technology, Nanjing University, Nanjing, China 2Jiangsu University of Science and Technology Zhenjiang, China
Pseudocode No The paper does not contain any pseudocode or clearly labeled algorithm blocks.
Open Source Code No The paper does not provide any concrete access to source code for the described methodology.
Open Datasets Yes Datasets We evaluated the proposed approach on three public benchmark datasets: i Coseg [Batra et al., 2010], MSRC [Winn et al., 2005] and Cosal2015 [Zhang et al., 2016]. ...We select the widely used pre-trained VGG 16-layer net [Simonyan and Zisserman, 2014] (over the MS COCO dataset [Lin et al., 2014])...
Dataset Splits No For the sake of fair comparison, we following the same setting in [Wei et al., 2017; Zheng et al., 2018], the training groups are randomly selected from a subset of COCO dataset (which has 9213 images with pixelwised ground-truth) using the global similarity (Gist and Lab color histogram features), and then fine-tune the model by randomly selecting 50% 50% training-test images for three datasets. The paper mentions training and testing splits but does not explicitly define a validation split.
Hardware Specification No The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running its experiments.
Software Dependencies No The paper mentions using a 'pre-trained VGG 16-layer net' and optimization by 'standard SGD', but does not specify software dependencies with version numbers.
Experiment Setup Yes The proposed models are optimized by standard SGD in which the momentum parameter is chosen as 0.99, the learning rate is set to 1e-5, and the weight decay is 0.0005. We need about 50000 training iterations for convergence. And for co-perceptual loss, we follow the setting in Neural Style Transfer and use the activated layers Relu3 1, Relu4 1, Relu5 1 of VGG as the hidden representation. And the loss tradeoff parameter λ is set to be 0.1 in our work.