A Survey on Learning to Hash
来源:互联网 发布:python smtp tls 编辑:程序博客网 时间:2024/05/15 02:26
Motivation: Storage efficiency and Retrieval efficiency.
Locality sensitive hashing and learning to hash.
Data independent(LSH) and data dependent(Learning to Hash).
Learning to hash:
pairwise similarity preserving, multiwise similarity preserving, implicit similarity preserving, and quantization.
Future:
End to end learning strategy for real application, directly learning the hash codes from the object, e.g., image, instead of first learning the representations and then learning the hash codes from the representation.
To improve the recall, two methods are adopted
1 take more hashing tables. 2 one hashing table and retrieval more buckets.
Retrieval:
1 find the nearest buckets, and use other hashing codes or original feature to make a re-rank.
- A Survey on Learning to Hash
- A Survey on Transfer Learning
- 理解《A Survey on Transfer Learning》
- 论文阅读:A Survey on Transfer Learning
- A Survey of Deep Learning Techniques Applied to Trading
- A brief survey on MCUs
- A Survey On Relation Extraction
- 【迁移学习——1】2010-A Survey on Transfer Learning
- A Quick Survey on Automatic Unpacking Techniques
- A SURVEY ON AUTOMATIC TEST CASE GENERATION
- A Survey on Automatic Text Summarization
- learning to hash
- Learning to Hash
- Learning to Hash
- learning to hash
- [论文学习]Deep Learning Based Recommendation: A Survey
- Deep Learning based Recommender System: A Survey and New Perspectives
- What's on CIO agendas in 2007: A McKinsey Survey
- Java 泛型学习 泛型擦除带来的不自然
- [leetcode][DP] Best Time to Buy and Sell Stock III
- 第三章第20题
- 第三章 39,40
- web使用ssh开发异常总结
- A Survey on Learning to Hash
- 操作系统书籍推荐
- POJ 3398 Perfect Service(树形DP,最小支配集)
- html 标签: image也能提交form!!!
- armv8 ARM64 AARCH64
- Redis,Memcache,mongoDB的区别
- find
- 放棋子
- 单链表的操作