MIHash: Online Hashing with Mutual Information

@article{akir2017MIHashOH,
  title={MIHash: Online Hashing with Mutual Information},
  author={Fatih Çakir and Kun He and Sarah Adel Bargal and Stan Sclaroff},
  journal={2017 IEEE International Conference on Computer Vision (ICCV)},
  year={2017},
  pages={437-445}
}
Learning-based hashing methods are widely used for nearest neighbor retrieval, and recently, online hashing methods have demonstrated good performance-complexity trade-offs by learning hash functions from streaming data. In this paper, we first address a key challenge for online hashing: the binary codes for indexed data must be recomputed to keep pace with updates to the hash functions. We propose an efficient quality measure for hash functions, based on an information-theoretic quantity… 

Figures and Tables from this paper

Online Hashing with Similarity Learning
TLDR
This paper proposes a novel online hashing framework without updating binary codes that is competitive or outperforms the state-of-the-art online hashing methods in terms of both accuracy and efficiency for multilabel image retrieval.
Online Hashing With Bit Selection for Image Retrieval
TLDR
This paper proposes a new online hashing method in which the target codes are constructed according to the data characteristics and are used to learn the hash functions online, and the learned hash functions are resistant to the bit-flipping error.
Online Supervised Sketching Hashing for Large-Scale Image Retrieval
TLDR
This paper proposes an online supervised hashing method in which a semantic similarity graph is designed to describe the data similarity according to the supervised information, and a data sketch is developed to preserve the characteristics of the graph with significantly smaller size in the online settings.
Hashing with Mutual Information
TLDR
It is shown that optimizing mutual information can reduce ambiguity in the induced neighborhood structure in the learned Hamming space, which is essential in obtaining high retrieval performance.
Towards Optimal Discrete Online Hashing with Balanced Similarity
TLDR
A novel balanced similarity is further proposed, which uses two equilibrium factors to balance the similar and dissimilar weights and eventually enables the usage of discrete optimizations in online hashing.
Hadamard Matrix Guided Online Hashing
TLDR
A novel supervised online hashing scheme termed H adamard M atrix Guided O nline H ashing (HMOH) is proposed, which introduces Hadamard matrix, which is an orthogonal binary matrix built via Sylvester method, which satisfies several desired properties of hashing codes.
Supervised Online Hashing via Similarity Distribution Learning
TLDR
This paper proposes to model the similarity distributions between the input data and the hashing codes, upon which a novel supervised online hashing method, dubbed as Similarity Distribution based Online Hashing (SDOH), is proposed, to keep the intrinsic semantic relationship in the produced Hamming space.
Online Hashing with Efficient Updating of Binary Codes
TLDR
A novel online hashing framework to update the binary codes efficiently without accumulating the whole database is proposed and the hash functions are fixed and the projection functions are introduced to learn online from the streaming data.
Fast Class-Wise Updating for Online Hashing
TLDR
A novel supervised online hashing scheme is proposed to address the above two challenges by introducing a novel and efficient inner product operation, and quantitatively demonstrated that the collective effort of class-wise updating and semi-relaxation optimization provides a superior performance comparing to various state-of-the-art methods.
...
...

References

SHOWING 1-10 OF 33 REFERENCES
Online Hashing
TLDR
This paper proposes an online hash model to accommodate data coming in stream for online learning, and extends the online hashing (OH) from a single model to a multimodel OH that trains multiple models so as to retain diverse OH models in order to avoid biased update.
Adaptive Hashing for Fast Similarity Search
TLDR
In experiments with three image retrieval benchmarks, the proposed online algorithm attains retrieval accuracy that is comparable to competing state-of-the-art batch-learning solutions, while the formulation is orders of magnitude faster and being online it is adaptable to the variations of the data.
Learning to Hash with Binary Reconstructive Embeddings
TLDR
An algorithm for learning hash functions based on explicitly minimizing the reconstruction error between the original distances and the Hamming distances of the corresponding binary embeddings is developed.
Online supervised hashing
Fast Supervised Hashing with Decision Trees for High-Dimensional Data
TLDR
Experiments demonstrate that the proposed method significantly outperforms most state-of-the-art methods in retrieval precision and training time, and is orders of magnitude faster than many methods in terms of training time.
Supervised hashing with kernels
TLDR
A novel kernel-based supervised hashing model which requires a limited amount of supervised information, i.e., similar and dissimilar data pairs, and a feasible training cost in achieving high quality hashing, and significantly outperforms the state-of-the-arts in searching both metric distance neighbors and semantically similar neighbors is proposed.
Ranking Preserving Hashing for Fast Similarity Search
TLDR
This paper proposes a novel Ranking Preserving Hashing (RPH) approach that directly optimizes a popular ranking measure, Normalized Discounted Cumulative Gain (NDCG), to obtain effective hashing codes with high ranking accuracy.
Online sketching hashing
TLDR
A novel approach to handle these two problems simultaneously based on the idea of data sketching, which can learn hash functions in an online fashion, while needs rather low computational complexity and storage space.
Supervised Discrete Hashing
TLDR
This work proposes a new supervised hashing framework, where the learning objective is to generate the optimal binary hash codes for linear classification, and introduces an auxiliary variable to reformulate the objective such that it can be solved substantially efficiently by employing a regularization algorithm.
Feature Learning Based Deep Supervised Hashing with Pairwise Labels
TLDR
Experiments show that the proposed deep pairwise-supervised hashing method (DPSH), to perform simultaneous feature learning and hashcode learning for applications with pairwise labels, can outperform other methods to achieve the state-of-the-art performance in image retrieval applications.
...
...