Hashing image retrieval source code and database summary

The following hash algorithm summary from this week's weekly report, originally did not intend to post, but, considering that these resources are concerned about the use of hashing algorithms for large-scale image search crossing should be very useful, so good things this kid will not be hiding. The most important collection principle of this resource is the original author's homepage on whether the source code, in order to each method of information as complete as possible, the kid will be as far as possible in addition to provide the source, but also give the PDF article link, project homepage, slide and so on.

To re-investigate the hashing method, the right figure is found to provide a partial source of the hash method, which contains a comparison of the classic hashing methods, such as E2lsh, MIH, but also contains some recent years until 13 introduced some of the relatively new hashing algorithm, such as the 13 proposed by the BPBC, OPQ, Ksh

The above paragraph is excerpted from the boy's weekly newspaper (this week, in addition to the boy to change an article, the rest of the time almost all in soy sauce, who called the boss does not pay, O (∩_∩) o~), the reference to the "right" can be skipped, directly see the following different hash algorithm link information.

Hashing method

To advertise the code:

2. AGH: Hashing with Graphs [Paper] [Code]
4. BPBC: Learning Binary Codes for high-dimensional Data Using Bilinear projections [Paper] [Code]
6. BRE: Learning to Hash with Binary reconstructive embeddings [Paper] [Code]
8. DBQ: Double-bit quantization for hashing [Paper] [Code]
10. e2lsh: Local sensitive Hash [Project Page] read
12. HDML: Hamming Distance Metric Learning [Paper] [Code]
14. IMH: Inter-media Hashing for large-scale retrieval from heterogenous Data Sources [Project Page][code]
16. Isoh: Isotropic Hashing [Paper] [Code]
18. ITQ: iterative quantization:a Procrustean approach to learning Binary Codes [Project page][paper] [Code] Rea D
20. klsh: kernelized locality-sensitive Hashing for Scalable Image Search [Project Page] [Paper][code]
22. KMH: K-means hashing:an affinity-preserving quantization Method for learning Binary Compact Codes [Paper] [Code] Read
24. KSH: Supervised Hashing with kernels [Paper] [Code] Read
26. mdsh: Multidimensional spectral Hashing [Paper] [Code]
28. MH: Manhattan hashing for large-scale image retrieval [Paper] [Code] Read
30. MLH: Minimal Loss Hashing for Compact Binary Codes [Paper] [Code] [Slide] (kmh mentioned MLH is a semi-supervised hash)
32. OPQ: Optimized Product quantization for approximate Nearest Neighbor Search [Paper] [Code]
34. SH: Spectral Hashing [Paper] [Code] Read
36. IHM: Inductive Hashing on Manifolds (CVPR) projectpage Read
38. BSPH: semi-supervised nonlinear Hashing Using Bootstrap sequential Projection Learning (+ tkde) projectpage read
40. Fasthash: Fast supervised Hashing with decision Trees for High-dimensional Data (CVPR) [Code] Read
42. spherical Hashing: Spherical Hashing (CVPR)read

No code:

1. PDH: Predictable dual-view Hashing (ICML2013) read

Common Database

1. LabelMe
2. Min-loss-hashing

People of concern

Note: The following code for different hashing methods can be found on their home page

• Grauman

  Image search and large-scale retrieval series paper

• Norouzi

  Hamming Distance Metric Learning

  Fast Search in Hamming Space with Multi-Index Hashing

  Minimal Loss Hashing for Compact Binary Codes code

• Fergus

  Spectral Hashing Read

  Multidimensional Spectral Hashing

• Chhshen & Guosheng Lin

  A General two-step approach to learning-based hashing (CVPR)code in BitBucket
  Read notes

  Learning hash functions using column generation (ICML)code in BitBucket

  Fast supervised Hashing with decision Trees (CVPR) Papercode in BitBucket read

• Yunchao

  Iterative quantization (CVPR)Project page read

  Angular quantization-based Binary Codes for Fast similarity Search (NIPS)Project page

  Learning Binary Codes for high-dimensional Data Using Bilinear Projections (CVPR)Project page

• Kahe

  K-means Hashing (CVPR)code link from his homepage read

  Optimized Product Quantization (CVPR)Project page

• June Wang

• *Wei Liu *

• XianglongLiu, teacher Liu, who started hashing in 2012 and published a series of papers, is a scholar who makes a hash earlier in the country, and has some code on his homepage that he publishes in a hash article.

Others explain some of papers's good posts

• Random projection method of Locality sensitive Hashing (LSH)
• Semi-supervised Hashing
• Spherical Hashing

Non-hashing methods

• Liangzheng
  • Packing and padding:coupled Multi-Index for accurate Image retrieval
  • Bayes merging of multiple vocabularies for scalable Image retrieval
  • Lp-norm IDF for Large scale Image Search
  • Visual phraselet:refining Spatial Constraints for Large scale Image Search

Thank you for these release code of the Great God, this small shuo to you with a high respect, if you crossing found that there is not included, please leave a message in order to complement the complete.

From:http://yongyuan.name/blog/codes-of-hash-for-image-retrieval.html

Hashing image retrieval source code and database summary