Generative Extension Positive Pairs and Improving Sample Selection Based on Contrastive Learning for Unsupervised Person Re-identification
學年 112
學期 2
發表日期 2024-04-14
作品名稱 Generative Extension Positive Pairs and Improving Sample Selection Based on Contrastive Learning for Unsupervised Person Re-identification
作品名稱(其他語言)
著者 Zheng-An Zhu; Chen-Kuo Chiang
作品所屬單位
出版者
會議名稱 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing
會議地點 Seoul, Korea
摘要 In this paper, we present Generative Extension Positive Pairs (GEPP), a novel approach to enhance unsupervised person re-identification (re-id) through contrastive learning. Data generation and pair selection methods significantly impact model performance in contrastive learning. To improve positive pair generation, we incorporate a Generative Adversarial Network (GAN) to create novel views as augmentation samples. We also introduce a sample selection scheme in the contrastive learning process to effectively choose GAN-augmented positive samples. Leveraging our sample selection results, we construct the GEPP framework and propose a unique loss function for contrastive learning. Experimental results showcase that our generative extension of positive pairs and sample selection method offer a versatile, automated, and diverse approach, achieving higher mean average precision (mAP) in re-id tasks than conventional data augmentation techniques. Additionally, our framework outperforms existing state-of-the-art methods on the Market-1501 and MSMT17 datasets.
關鍵字
語言 zh_TW
收錄於
會議性質 國內
校內研討會地點
研討會時間 20240414~20240419
通訊作者
國別 KOR
公開徵稿
出版型式
出處
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/127134 )