原创 Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-Identification
行人重識別之注意力機制 Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-Identification 原文鏈
2020-02-25 06:58:50
原创 Learning to Reduce Dual-level Discrepancy for Infrared-Visible Person Re-identification
行人重識別之紅外圖像識別（CVPR2019） Learning to Reduce Dual-level Discrepancy for Infrared-Visible Person Re-identification 原文鏈接
2020-02-25 06:58:50
原创 Distilled Person Re-identification: Towards a More Scalable System
行人重識別之泛化能力 Distilled Person Re-identification: Towards a More Scalable System 原文鏈接：http://openaccess.thecvf.com/con
2020-02-25 06:58:50
原创 Densely Semantically Aligned Person Re-Identification
行人重識別之語義分割網絡 Densely Semantically Aligned Person Re-Identification 原文鏈接：http://openaccess.thecvf.com/content_CVPR_2
2020-02-25 06:58:50
原创 AlignedReID: Surpassing Human-Level Performance in Person Re-Identification
行人重識別之局部特徵 AlignedReID: Surpassing Human-Level Performance in Person Re-Identification 原文鏈接：https://arxiv.org/pdf/1
2020-02-25 06:58:50
原创 EANet: Enhancing Alignment for Cross-Domain Person Re-identification
行人重識別之cross domain EANet: Enhancing Alignment for Cross-Domain Person Re-identification (2018arXiv) 原文鏈接 這篇文章從align
2020-02-25 06:58:50
原创 AANet: Attribute Attention Network for Person Re-Identifications
行人重識別之多信息融合 AANet: Attribute Attention Network for Person Re-Identifications 原文鏈接：http://openaccess.thecvf.com/cont
2020-02-25 06:58:50
原创 Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-id
行人重識別之局部識別（CVPR2019） Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-i
2020-02-25 06:58:50
原创 22行代碼（python）快速實現KNN及可視化（附數據下載鏈接）
本文使用簡單的例子，使用22行代碼（刨除註釋），快速實現knn。爲了更加方便理解，沒有使用knn的函數，只是用了簡單的矩陣操作和計數操作，希望對初學者有幫助。 先來看看數據的格式： （下載地址：鏈接：https://pan.b
2020-02-25 06:58:50
原创 Improving Person Re-identification by Attribute and Identity Learning
行人重識別之行人屬性 Improving Person Re-identification by Attribute and Identity Learning 原文鏈接：https://arxiv.org/pdf/1703.07
2020-02-25 06:58:50
原创 Ranked List Loss for Deep Metric Learning
CVPR2019 度量學習 Ranked List Loss for Deep Metric Learning 原文鏈接：https://arxiv.org/abs/1903.03238 度量學習在圖像識別、檢索等領域有着廣泛應用
2020-02-25 06:58:50
原创 VGG Net、GoogLe Net、Squeezed Net、Mobile Net、Shuffle Net、Res Net梳理與網絡優化
摘要：深度學習不能僅僅停留在理論層面，更重要的是爲人所用。但是如下圖所示，深度神經網絡應用於實際生活，還有很多困難。所以將網絡模型部署到存儲空間更小、計算力更低的可移動設備上對於深度學習的發展至關重要。這篇文章從以上角度對一些經典
2020-02-25 06:58:50