STDP-Net: Improved Pedestrian Attribute Recognition Using Swin Transformer and Semantic Self-Attentionopen access
- Authors
- Lee, Geonu; Cho, Jungchan
- Issue Date
- Aug-2022
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Transformers; Semantics; Decoding; Head; Convolution; Task analysis; Image recognition; Deep learning; pedestrian attribute recognition; self-attention; transformer
- Citation
- IEEE ACCESS, v.10, pp.82656 - 82667
- Journal Title
- IEEE ACCESS
- Volume
- 10
- Start Page
- 82656
- End Page
- 82667
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85564
- DOI
- 10.1109/ACCESS.2022.3196650
- ISSN
- 2169-3536
- Abstract
- An image location requiring focus to recognize a specific pedestrian attribute often depends on the state of the pedestrian within the image. In addition, various pedestrian attributes are closely related to each other. For example, the "Boots" and "ShortSkirt" attributes are related to the "Female" attribute. For these reasons, we propose a novel encoder-decoder network for pedestrian attribute recognition, called Swin Transformer and Decoder for Pedestrian attribute recognition Network (STDP-Net). First, we utilize a Swin Transformer that uses self-attention as the encoder. This allows the proposed method to understand the relative relationship between the spatial regions of the images, unlike conventional convolution-based methods. This enables an accurate recognition of the attributes, even in misaligned pedestrian image inputs. Second, we add a transformer decoder with learnable attribute queries to the encoder to understand the semantic relationships among the attributes. Using the decoder, the proposed method captures such relationships based on the self-attention of the attribute queries. Extensive experimental results demonstrate that the proposed method achieves a state-of-the-art performance on six pedestrian attribute recognition datasets. In addition, misalignment experiments on the PETA, PA100K, and RAP datasets show the superiority of the encoder-decoder structure in comparison with other state-of-the-art methods.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - IT융합대학 > 소프트웨어학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/85564)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.