Clothing Retrieval With Visual Attention Model

Abstract

Clothing retrieval is a challenging problem in computer vision. With the advance of Convolutional Neural Networks (CNNs), the accuracy of clothing retrieval has been significantly improved. FashionNet[1], a recent study, proposes to employ a set of artificial features in the form of landmarks for clothing retrieval, which are shown to be helpful for retrieval. However, the landmark detection module is trained with strong supervision which requires considerable efforts to obtain. In this paper, we propose a self-learning Visual Attention Model (VAM) to extract attention maps from clothing images. The VAM is further connected to a global network to form an end-to-end network structure through Impdrop connection which randomly Dropout on the feature maps with the probabilities given by the attention map. Extensive experiments on several widely used benchmark clothing retrieval data sets have demonstrated the promise of the proposed method. We also show that compared to the trivial Product

Stats

• citations40
• S2 citations—
• github stars0
• HF likes0
• heat score12.10
• arxiv keywang2017clothing

Related papers

• Where To Look And How To Describe: Fashion Image Retrieval With An Attentional Heterogeneous Bilinear Network (2020)11.19
• Looking At Outfit To Parse Clothing (2017)0.00
• An Effective Pipeline For A Real-world Clothes Retrieval System (2020)0.00
• Fashion Image Retrieval With Capsule Networks (2019)11.08
• Cross-domain Image Retrieval With Attention Modeling (2017)13.74
• A Generic Visualization Approach For Convolutional Neural Networks (2020)6.34
• Automatic Spatially-aware Fashion Concept Discovery (2017)16.82
• Channel Recurrent Attention Networks For Video Pedestrian Retrieval (2020)0.00