Unsupervised Person Re-identification: Clustering and Fine-tuning
1、介紹 基於全監督的行人重識別問題取得了很大的進展。但是基於無監督的行人重識別問題的進展則相對緩慢。現有研究主要集中在人工提取特徵然後使用無監督方法分類上，針對的數據集規模也比較小。作者提出了一個PUL(PROGRESSIVE UNSUPERVISED LEARNING)的方法，率先把深度學習框架應用到大規模數據集無監督行人重識別問題上。 2、作者的方法 作者將他的方法命名爲PUL(PROGRE
相關文章
- 1. Unsupervised Person Re-identification: Clustering and Fine-tuning
- 2. Unsupervised Person Re-identification: Clustering and Fine-tuning閱讀筆記
- 3. TOMM2018_Unsupervised Person Re-identification: Clustering and Fine-tuning
- 4. Clustering - Unsupervised learning introduction
- 5. Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
- 6. Pseudo Label Based on Multiple Clustering for Unsupervised Cross-Domain Person Re-Identification
- 7. Unsupervised clustering reveals new prostate cancer subtypes
- 8. Machine learning(7): Unsupervised learning-------CLUSTERING
- 9. Unsupervised Deep Embedding for Clustering Analysis(DEC)
- 10. Stepwise Metric Promotion for Unsupervised Video Person Re-identification
- 更多相關文章...
- • W3C RDF and OWL 活動 - W3C 教程
- • XSL-FO table-and-caption 對象 - XSL-FO 教程
- • RxJava操作符（七）Conditional and Boolean
- • Java 8 Stream 教程
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. Unsupervised Person Re-identification: Clustering and Fine-tuning
- 2. Unsupervised Person Re-identification: Clustering and Fine-tuning閱讀筆記
- 3. TOMM2018_Unsupervised Person Re-identification: Clustering and Fine-tuning
- 4. Clustering - Unsupervised learning introduction
- 5. Variational Deep Embedding: An Unsupervised and Generative Approach to Clustering
- 6. Pseudo Label Based on Multiple Clustering for Unsupervised Cross-Domain Person Re-Identification
- 7. Unsupervised clustering reveals new prostate cancer subtypes
- 8. Machine learning(7): Unsupervised learning-------CLUSTERING
- 9. Unsupervised Deep Embedding for Clustering Analysis(DEC)
- 10. Stepwise Metric Promotion for Unsupervised Video Person Re-identification