Unsupervised Hashing with Contrastive Information Bottleneck
- URL: http://arxiv.org/abs/2105.06138v1
- Date: Thu, 13 May 2021 08:30:16 GMT
- Title: Unsupervised Hashing with Contrastive Information Bottleneck
- Authors: Zexuan Qiu, Qinliang Su, Zijing Ou, Jianxing Yu and Changyou Chen
- Abstract summary: We propose to adapt a framework to learn binary hashing codes.
Specifically, we first propose to modify the objective function to meet the specific requirement of hashing.
We then introduce a probabilistic binary representation layer into the model to facilitate end-to-end training.
- Score: 39.607741586731336
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Many unsupervised hashing methods are implicitly established on the idea of
reconstructing the input data, which basically encourages the hashing codes to
retain as much information of original data as possible. However, this
requirement may force the models spending lots of their effort on
reconstructing the unuseful background information, while ignoring to preserve
the discriminative semantic information that is more important for the hashing
task. To tackle this problem, inspired by the recent success of contrastive
learning in learning continuous representations, we propose to adapt this
framework to learn binary hashing codes. Specifically, we first propose to
modify the objective function to meet the specific requirement of hashing and
then introduce a probabilistic binary representation layer into the model to
facilitate end-to-end training of the entire model. We further prove the strong
connection between the proposed contrastive-learning-based hashing method and
the mutual information, and show that the proposed model can be considered
under the broader framework of the information bottleneck (IB). Under this
perspective, a more general hashing model is naturally obtained. Extensive
experimental results on three benchmark image datasets demonstrate that the
proposed hashing method significantly outperforms existing baselines.
Related papers
- Adversarial Robustification via Text-to-Image Diffusion Models [56.37291240867549]
Adrial robustness has been conventionally believed as a challenging property to encode for neural networks.
We develop a scalable and model-agnostic solution to achieve adversarial robustness without using any data.
arXiv Detail & Related papers (2024-07-26T10:49:14Z) - RREH: Reconstruction Relations Embedded Hashing for Semi-Paired Cross-Modal Retrieval [32.06421737874828]
Reconstruction Relations Embedded Hashing (RREH) is designed for semi-paired cross-modal retrieval tasks.
RREH assumes that multi-modal data share a common subspace.
anchors are sampled from paired data, which improves the efficiency of hash learning.
arXiv Detail & Related papers (2024-05-28T03:12:54Z) - Enhancing Multiple Reliability Measures via Nuisance-extended
Information Bottleneck [77.37409441129995]
In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition.
We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training.
We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
arXiv Detail & Related papers (2023-03-24T16:03:21Z) - CoopHash: Cooperative Learning of Multipurpose Descriptor and Contrastive Pair Generator via Variational MCMC Teaching for Supervised Image Hashing [42.67510119856105]
generative models, such as Generative Adversarial Networks (GANs), can generate synthetic data in an image hashing model.
GANs are difficult to train, which prevents hashing approaches from jointly training the generative models and the hash functions.
We propose a novel framework, the generative cooperative hashing network, which is based on energy-based cooperative learning.
arXiv Detail & Related papers (2022-10-09T15:42:36Z) - Deep Asymmetric Hashing with Dual Semantic Regression and Class
Structure Quantization [9.539842235137376]
We propose a dual semantic asymmetric hashing (DSAH) method, which generates discriminative hash codes under three-fold constrains.
With these three main components, high-quality hash codes can be generated through network.
arXiv Detail & Related papers (2021-10-24T16:14:36Z) - 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) - Integrating Semantics and Neighborhood Information with Graph-Driven
Generative Models for Document Retrieval [51.823187647843945]
In this paper, we encode the neighborhood information with a graph-induced Gaussian distribution, and propose to integrate the two types of information with a graph-driven generative model.
Under the approximation, we prove that the training objective can be decomposed into terms involving only singleton or pairwise documents, enabling the model to be trained as efficiently as uncorrelated ones.
arXiv Detail & Related papers (2021-05-27T11:29:03Z) - Mixing Consistent Deep Clustering [3.5786621294068373]
Good latent representations produce semantically mixed outputs when decoding linears of two latent representations.
We propose the Mixing Consistent Deep Clustering method which encourages representations to appear realistic.
We show that the proposed method can be added to existing autoencoders to further improve clustering performance.
arXiv Detail & Related papers (2020-11-03T19:47:06Z) - CIMON: Towards High-quality Hash Codes [63.37321228830102]
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.
arXiv Detail & Related papers (2020-10-15T14:47:14Z) - Unsupervised Deep Cross-modality Spectral Hashing [65.3842441716661]
The framework is a two-step hashing approach which decouples the optimization into binary optimization and hashing function learning.
We propose a novel spectral embedding-based algorithm to simultaneously learn single-modality and binary cross-modality representations.
We leverage the powerful CNN for images and propose a CNN-based deep architecture to learn text modality.
arXiv Detail & Related papers (2020-08-01T09:20:11Z)
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.