Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identificatio
Author Xinyu Zhang Jiewei Cao Conference ICCV 2019 Motivation 現有的pseudo label estimation高度依賴於聚類結果，所以需要一種漸進的方式來逐步學到可信的僞標籤。 Contribution 提出一種self-train的漸近式的framwork，總共分成兩步conservative stage和promoting st
相關文章
- 1. 論文解讀：Self-training with progressive augmentation for unsupervised person re-ID（PAST）
- 2. Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification
- 3. 【PLPR】Progressive Learning for Person Re-Identification with One Example
- 4. Unsupervised Data Augmentation for Consistency Training
- 5. 2019 CVPR之ReID：Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-
- 6. Unsupervised Data Augmentation For Consistency Training 論文閱讀
- 7. Stepwise Metric Promotion for Unsupervised Video Person Re-identification
- 8. Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification
- 9. 【FSR】Feature Space Regularization for Person Re-Identification with One Sample
- 10. Unsupervised Person Re-identification: Clustering and Fine-tuning
- 更多相關文章...
- • Swift for 循環 - Swift 教程
- • Scala for循環 - Scala教程
- • Java 8 Stream 教程
- • 爲了進字節跳動，我精選了29道Java經典算法題，帶詳細講解
相關標籤/搜索
每日一句
-
每一个你不满意的现在，都有一个你没有努力的曾经。
歡迎關注本站公眾號,獲取更多信息
相關文章
- 1. 論文解讀：Self-training with progressive augmentation for unsupervised person re-ID（PAST）
- 2. Self-Training With Progressive Augmentation for Unsupervised Cross-Domain Person Re-Identification
- 3. 【PLPR】Progressive Learning for Person Re-Identification with One Example
- 4. Unsupervised Data Augmentation for Consistency Training
- 5. 2019 CVPR之ReID：Towards Rich Feature Discovery with Class Activation Maps Augmentation for Person Re-
- 6. Unsupervised Data Augmentation For Consistency Training 論文閱讀
- 7. Stepwise Metric Promotion for Unsupervised Video Person Re-identification
- 8. Asymmetric Co-Teaching for Unsupervised Cross-Domain Person Re-Identification
- 9. 【FSR】Feature Space Regularization for Person Re-Identification with One Sample
- 10. Unsupervised Person Re-identification: Clustering and Fine-tuning