Semantic Locality-Aware Deformable Network for Clothing Segmentation

Authors: Wei Ji, Xi Li, Yueting Zhuang, Omar El Farouk Bourahla, Yixin Ji, Shihao Li, Jiabao Cui

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

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results demonstrate the effectiveness of the proposed model against the state-of-the-art approaches. Table 1 shows the performance of our method compared with various baselines. Results show that we achieve the state-of-the-art performance in accuracy in three datasets.
Researcher Affiliation Collaboration Wei Ji1, Xi Li1,2 , Yueting Zhuang1 , Omar El Farouk Bourahla1, Yixin Ji1, Shihao Li1, Jiabao Cui1 1 Zhejiang University, Hangzhou, China 2 Alibaba-Zhejiang University Joint Institute of Frontier Technologies, Hangzhou, China
Pseudocode Yes Algorithm 1: Clothing segmentation with semantic locality-aware deformable network
Open Source Code No The paper does not provide any statement regarding the availability of its source code, nor does it include a link to a code repository.
Open Datasets Yes In order to evaluate the performance of the proposed approach, we conduct a set of qualitative and quantitative experiments on two benchmark datasets annotated with pixel-wise groundtruth labeling, including Fashionista [Yamaguchi et al., 2012], refined Fashionista [Tangseng et al., 2017], and CFPD [Liu et al., 2014].
Dataset Splits Yes For the set of training and testing, we randomly divide the Fashionista dataset into train-test splits the same as [Yamaguchi et al., 2012] with 10% of training images leaving for validation, and divide CFPD dataset into 90% train-set and 10% test-set, the same as Fashionista.
Hardware Specification Yes We implement our architecture by using the Caffe [Jia et al., 2014] toolbox and NVIDIA TITAN X GPU to train the network.
Software Dependencies No The paper mentions using 'Caffe [Jia et al., 2014] toolbox' but does not specify its version number or any other software dependencies with specific versions.
Experiment Setup Yes The networks are trained in the CFPD and Fashionista training dataset with Adam optimization with β1 = 0.9 and β2 = 0.999. The learning rate is set to 1e-4, batch size is 1 with the consideration of GPU memory, and the weight decay is 0.0005. The reconstruction loss with the balance parameter λ = 0.125... We need about 100K training iterations for convergence.