ML p(r)ior | Unsupervised Deep Hashing for Large-scale Visual Search

Unsupervised Deep Hashing for Large-scale Visual Search

2016-01-31
Learning based hashing plays a pivotal role in large-scale visual search. However, most existing hashing algorithms tend to learn shallow models that do not seek representative binary codes. In this paper, we propose a novel hashing approach based on unsupervised deep learning to hierarchically transform features into hash codes. Within the heterogeneous deep hashing framework, the autoencoder layers with specific constraints are considered to model the nonlinear mapping between features and binary codes. Then, a Restricted Boltzmann Machine (RBM) layer with constraints is utilized to reduce the dimension in the hamming space. Extensive experiments on the problem of visual search demonstrate the competitiveness of our proposed approach compared to state-of-the-art.
PDF

Highlights - Most important sentences from the article

Login to like/save this paper, take notes and configure your recommendations

Related Articles

2018-03-02

Binary vector embeddings enable fast nearest neighbor retrieval in large databases of high-dimension… show more
PDF

Highlights - Most important sentences from the article

2017-08-17
1708.05127 | cs.CV

With the increasing demand of massive multimodal data storage and organization, cross-modal retrieva… show more
PDF

Highlights - Most important sentences from the article

2015-08-13

In this paper we introduce a novel hash learning framework that has two main distinguishing features… show more
PDF

Highlights - Most important sentences from the article

2018-03-06
1803.02284 | cs.CV

Recent studies show that large-scale sketch-based image retrieval (SBIR) can be efficiently tackled … show more
PDF

Highlights - Most important sentences from the article

2018-06-15

Many approaches to semantic image hashing have been formulated as supervised learning problems that … show more
PDF

Highlights - Most important sentences from the article

2017-12-22
1712.08315 | cs.CV

This paper proposes an end-to-end deep hashing framework with category mask for fast video retrieval… show more
PDF

Highlights - Most important sentences from the article

2018-01-04

Many of the existing machine learning algorithms, both supervised and unsupervised, depend on the qu… show more
PDF

Highlights - Most important sentences from the article

2017-02-02

Learning to hash has been widely applied to approximate nearest neighbor search for large-scale mult… show more
PDF

Highlights - Most important sentences from the article

2015-07-01
1507.00101 | cs.CV

This paper presents a simple yet effective supervised deep hash approach that constructs binary hash… show more
PDF

Highlights - Most important sentences from the article

2017-04-26
1704.08345 | cs.CV

Existing zero-shot learning (ZSL) models typically learn a projection function from a feature space … show more
PDF

Highlights - Most important sentences from the article

2018-11-27

Maintaining the pair similarity relationship among originally high-dimensional data into a low-dimen… show more
PDF

Highlights - Most important sentences from the article

2019-04-24

Representing images by compact hash codes is an attractive approach for large-scale content-based im… show more
PDF

Highlights - Most important sentences from the article

2019-04-25

Deep hashing has recently received attention in cross-modal retrieval for its impressive advantages.… show more
PDF

Highlights - Most important sentences from the article

2019-04-07

Learning-based hashing algorithms are ``hot topics" because they can greatly increase the scale at w… show more
PDF

Highlights - Most important sentences from the article

2019-02-22

In this paper, we propose a novel hash learning approach that has the following main distinguishing … show more
PDF

Highlights - Most important sentences from the article

2019-04-13
1904.06513 | cs.LG

In scientific fields, data sparsity greatly affects prediction performance. This study builds a deep… show more
PDF

Highlights - Most important sentences from the article