CIMON: Towards High-quality Hash Codes
- URL: http://arxiv.org/abs/2010.07804v4
- Date: Sat, 21 Aug 2021 04:13:07 GMT
- Title: CIMON: Towards High-quality Hash Codes
- Authors: Xiao Luo, Daqing Wu, Zeyu Ma, Chong Chen, Minghua Deng, Jinwen Ma,
Zhongming Jin, Jianqiang Huang and Xian-Sheng Hua
- Abstract summary: We propose a new method named textbfComprehensive stextbfImilarity textbfMining and ctextbfOnsistency leartextbfNing (CIMON)
First, we use global refinement and similarity statistical distribution to obtain reliable and smooth guidance. Second, both semantic and contrastive consistency learning are introduced to derive both disturb-invariant and discriminative hash codes.
- Score: 63.37321228830102
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Recently, hashing is widely used in approximate nearest neighbor search for
its storage and computational efficiency. Most of the unsupervised hashing
methods learn to map images into semantic similarity-preserving hash codes by
constructing local semantic similarity structure from the pre-trained model as
the guiding information, i.e., treating each point pair similar if their
distance is small in feature space. However, due to the inefficient
representation ability of the pre-trained model, many false positives and
negatives in local semantic similarity will be introduced and lead to error
propagation during the hash code learning. Moreover, few of the methods
consider the robustness of models, which will cause instability of hash codes
to disturbance. In this paper, we propose a new method named
{\textbf{C}}omprehensive s{\textbf{I}}milarity {\textbf{M}}ining and
c{\textbf{O}}nsistency lear{\textbf{N}}ing (CIMON). First, we use global
refinement and similarity statistical distribution to obtain reliable and
smooth guidance. Second, both semantic and contrastive consistency learning are
introduced to derive both disturb-invariant and discriminative hash codes.
Extensive experiments on several benchmark datasets show that the proposed
method outperforms a wide range of state-of-the-art methods in both retrieval
performance and robustness.
Related papers
- Learning to Hash Naturally Sorts [84.90210592082829]
We introduce Naturally-Sorted Hashing (NSH) to train a deep hashing model with sorted results end-to-end.
NSH sort the Hamming distances of samples' hash codes and accordingly gather their latent representations for self-supervised training.
We describe a novel Sorted Noise-Contrastive Estimation (SortedNCE) loss that selectively picks positive and negative samples for contrastive learning.
arXiv Detail & Related papers (2022-01-31T16:19:02Z) - Deep Self-Adaptive Hashing for Image Retrieval [16.768754022585057]
We propose a textbfDeep Self-Adaptive Hashing(DSAH) model to adaptively capture the semantic information with two special designs.
First, we construct a neighborhood-based similarity matrix, and then refine this initial similarity matrix with a novel update strategy.
Secondly, we measure the priorities of data pairs with PIC and assign adaptive weights to them, which is relies on the assumption that more dissimilar data pairs contain more discriminative information for hash learning.
arXiv Detail & Related papers (2021-08-16T13:53:20Z) - FDDH: Fast Discriminative Discrete Hashing for Large-Scale Cross-Modal
Retrieval [41.125141897096874]
Cross-modal hashing is favored for its effectiveness and efficiency.
Most existing methods do not sufficiently exploit the discriminative power of semantic information when learning the hash codes.
We propose Fast Discriminative Discrete Hashing (FDDH) approach for large-scale cross-modal retrieval.
arXiv Detail & Related papers (2021-05-15T03:53:48Z) - Deep Hashing with Hash-Consistent Large Margin Proxy Embeddings [65.36757931982469]
Image hash codes are produced by binarizing embeddings of convolutional neural networks (CNN) trained for either classification or retrieval.
The use of a fixed set of proxies (weights of the CNN classification layer) is proposed to eliminate this ambiguity.
The resulting hash-consistent large margin (HCLM) proxies are shown to encourage saturation of hashing units, thus guaranteeing a small binarization error.
arXiv Detail & Related papers (2020-07-27T23:47:43Z) - Self-Supervised Bernoulli Autoencoders for Semi-Supervised Hashing [1.8899300124593648]
This paper investigates the robustness of hashing methods based on variational autoencoders to the lack of supervision.
We propose a novel supervision method in which the model uses its label distribution predictions to implement the pairwise objective.
Our experiments show that both methods can significantly increase the hash codes' quality.
arXiv Detail & Related papers (2020-07-17T07:47:10Z) - Unsupervised Semantic Hashing with Pairwise Reconstruction [22.641786533525245]
We present Pairwise Reconstruction (PairRec), which is a discrete variational autoencoder based hashing model.
We experimentally compare PairRec to traditional and state-of-the-art approaches, and obtain significant performance improvements in the task of document similarity search.
arXiv Detail & Related papers (2020-07-01T10:54:27Z) - Generative Semantic Hashing Enhanced via Boltzmann Machines [61.688380278649056]
Existing generative-hashing methods mostly assume a factorized form for the posterior distribution.
We propose to employ the distribution of Boltzmann machine as the retrievalal posterior.
We show that by effectively modeling correlations among different bits within a hash code, our model can achieve significant performance gains.
arXiv Detail & Related papers (2020-06-16T01:23:39Z) - Procrustean Orthogonal Sparse Hashing [3.302605292858623]
We show that insect olfaction is structurally and functionally analogous to sparse hashing.
We present a novel method, Procrustean Orthogonal Sparse Hashing (POSH), that unifies these findings.
We propose two new methods, Binary OSL and SphericalHash, to address these deficiencies.
arXiv Detail & Related papers (2020-06-08T18:09:33Z) - Pairwise Supervised Hashing with Bernoulli Variational Auto-Encoder and
Self-Control Gradient Estimator [62.26981903551382]
Variational auto-encoders (VAEs) with binary latent variables provide state-of-the-art performance in terms of precision for document retrieval.
We propose a pairwise loss function with discrete latent VAE to reward within-class similarity and between-class dissimilarity for supervised hashing.
This new semantic hashing framework achieves superior performance compared to the state-of-the-arts.
arXiv Detail & Related papers (2020-05-21T06:11:33Z) - Reinforcing Short-Length Hashing [61.75883795807109]
Existing methods have poor performance in retrieval using an extremely short-length hash code.
In this study, we propose a novel reinforcing short-length hashing (RSLH)
In this proposed RSLH, mutual reconstruction between the hash representation and semantic labels is performed to preserve the semantic information.
Experiments on three large-scale image benchmarks demonstrate the superior performance of RSLH under various short-length hashing scenarios.
arXiv Detail & Related papers (2020-04-24T02:23:52Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.