Unabridged adjacent modulation for clothing parsing. (July 2022)

• Record Type: Journal Article
• Authors: Zhang, Dong; Zuo, Chengting; Wu, Qianhao; Fu, Liyong; Xiang, Xinguang
• Is Part Of: Pattern recognition. Volume 127(2022)
• Publication Date: 2022-07
• Subjects: Encoder-decoder network -- Clothing parsing -- Attention learning -- Features modulation -- Self-supervised learning; Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2022.108594
• Languages: English
• ISSNs: 0031-3203

Abstract

Highlights: Based on the encoder-decoder architecture, we propose a block-specific unabridged channel attention mechanism, such that features within each block can be recalibrated. A top-down adjacent modulation for decoder network is proposed so that the lowlevel features substantially contain abundant semantic contexts. We demonstrate the effectiveness of UAM-Net via two challenging benchmarks. Results declare that we can achieve a new state-of-the-art on colorful fashion parsing dataset and comparable performance on modified fashion clothing dataset with less computation overhead. Abstract: Clothing parsing has made tremendous progress in the domain of computer vision recently. Most state-of-the-art methods are based on the encoder-decoder architecture. However, the existing methods mainly neglect problems of feature uncalibration within blocks and semantics dilution between blocks. In this work, we propose an unabridged adjacent modulation network (UAM-Net) to aggregate multi-level features for clothing parsing. We first build an unabridged channel attention (UCA) mechanism on feature maps within each block for feature recalibration. We further design a top-down adjacent modulation (TAM) for decoder blocks. By deploying TAM, high-level semantic information and visual contexts can be gradually transferred into lower-level layers without loss. The joint implementation of UCA and TAM ensures that the encoder has an enhanced feature representation ability, and the low-level features of the decoders contain abundant semantic contexts. Quantitative and qualitative experimental results on two challenging benchmarks ( i.e ., colorful fashion parsing and the modified fashion clothing) declare that our proposed UAM-Net can achieve competitive high-accurate performance with the state-of-the-art methods. The source codes are available at: https://github.com/ctzuo/UAM-Net .