natural-language-processing-9

Deep Hashing

3260 papers • 126 benchmarks • 313 datasets

This task has no description! Would you like to contribute one?

(Image credit: Papersgraph)

Benchmarks

These leaderboards are used to track progress in deep-hashing-27

Trend

Dataset

Best Model

Actions

No benchmarks available.

Libraries

i

Use these libraries to find deep-hashing-27 models and implementations

jjmachan/DeepHash

2 papers 27

Datasets

No datasets available.

Subtasks

No subtasks available.

Most implemented papers

Deep Hashing Network for Unsupervised Domain Adaptation

Hemanth Venkateswara, José Eusébio, Shayok Chakraborty, S. Panchanathan•Wed Jun 21 2017

This is the first research effort to exploit the feature learning capabilities of deep neural networks to learn representative hash codes to address the domain adaptation problem and proposes a novel deep learning framework that can exploit labeled source data and unlabeled target data to learn informative hash codes, to accurately classify unseen target data.

2316

Content

0

Paper Graph

Greedy Hash: Towards Fast Optimization for Accurate Hash Coding in CNN

Yonghong Tian, Kai Han, Shupeng Su•Sun Dec 31 2017

This work adopts the greedy principle to tackle this NP hard problem by iteratively updating the network toward the probable optimal discrete solution in each iteration, and provides a new perspective to visualize and understand the effectiveness and efficiency of the algorithm.

222 0

Paper Graph

Targeted Attack for Deep Hashing based Retrieval

Shutao Xia, Jiawang Bai, B. Chen, Yiming Li, Dongxian Wu, Weiwei Guo, E. Yang•Tue Apr 14 2020

This paper proposes a novel method, dubbed deep hashing targeted attack (DHTA), to study the targeted attack on deep hashing based retrieval, which minimizes the average distance between the hash code of an adversarial example and those of a set of objects with the target label.

94 0

Paper Graph

Deep multi query image retrieval

C. Vural, Enver Akbacak•Wed Sep 30 2020

This study develops an efficient and fast multi- query image retrieval method when the queries are related to more than one semantic that outperforms similar multi-query image retrieval studies in terms of retrieval time and retrieval accuracy.

5 0

Paper Graph

One Loss for All: Deep Hashing with a Single Cosine Similarity based Learning Objective

T. Xiang, Yi-Zhe Song, Jiun Tian Hoe, KamWoh Ng, Chee Seng Chan•Tue Sep 28 2021

It is shown that maximizing the cosine similarity between the continuous codes and their corresponding binary orthogonal codes can ensure both hash code discriminativeness and quantization error minimization, leading to an one-loss deep hashing model that removes all the hassles of tuning the weights of various losses.

147 0

Paper Graph

Feature Learning Based Deep Supervised Hashing with Pairwise Labels

Wu-Jun Li, Sheng Wang, Wang-Cheng Kang•Wed Nov 11 2015

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.

703 0

Paper Graph

Deep Supervised Hashing with Triplet Labels

Kris M. Kitani, Xiaofang Wang, Yi Shi•Sat Nov 19 2016

A triplet label based deep hashing method which aims to maximize the likelihood of the given triplet labels, which outperforms all the baselines on CIFAR-10 and NUS-WIDE datasets, including the state-of-the-art method DPSH.

232 0

Paper Graph

Deep Discrete Hashing with Self-supervised Pairwise Labels

Lianli Gao, Jingkuan Song, Tao He, Hangbo Fan•Thu Jul 06 2017

Experimental results on standard datasets demonstrate that the proposed novel unsupervised deep hashing method, named Deep Discrete Hashing (DDH), significantly outperforms existing hashing methods by large margin in terms of mAP for image retrieval and object recognition.

14 0

Paper Graph

Binary Generative Adversarial Networks for Image Retrieval

Jingkuan Song•Mon Aug 07 2017

This paper uses binary generative adversarial networks (BGAN) to embed images to binary codes in an unsupervised way and significantly outperforms existing hashing methods by up to 107% in terms of mAP.

199 0

Paper Graph

Adding a benchmark result helps the community track progress.