Abstract | ||
---|---|---|
This work focuses on representing very high-dimensional global image descriptors using very compact 64-1024 bit binary hashes for instance retrieval. We propose DeepHash: a hashing scheme based on deep networks. Key to making DeepHash work at extremely low bitrates are three important considerations -- regularization, depth and fine-tuning -- each requiring solutions specific to the hashing problem. In-depth evaluation shows that our scheme consistently outperforms state-of-the-art methods across all data sets for both Fisher Vectors and Deep Convolutional Neural Network features, by up to 20 percent over other schemes. The retrieval performance with 256-bit hashes is close to that of the uncompressed floating point features -- a remarkable 512 times compression. |
Year | Venue | Field |
---|---|---|
2015 | CoRR | Data set,Pattern recognition,Floating point,Convolutional neural network,Computer science,Fine-tuning,Regularization (mathematics),Hash function,Artificial intelligence,Machine learning,Uncompressed video,Binary number |
DocType | Volume | Citations |
Journal | abs/1501.04711 | 7 |
PageRank | References | Authors |
0.53 | 36 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jie Lin | 1 | 51 | 4.73 |
Olivier Morère | 2 | 62 | 4.56 |
Vijay Chandrasekhar | 3 | 11 | 2.68 |
Antoine Veillard | 4 | 35 | 1.36 |
Hanlin Goh | 5 | 35 | 1.70 |