MOON: Multi-Hash Codes Joint Learning for Cross-Media Retrieval
- URL: http://arxiv.org/abs/2109.00883v1
- Date: Tue, 17 Aug 2021 14:47:47 GMT
- Title: MOON: Multi-Hash Codes Joint Learning for Cross-Media Retrieval
- Authors: Donglin Zhang, Xiao-Jun Wu, He-Feng Yin and Josef Kittler
- Abstract summary: Cross-media hashing technique has attracted increasing attention for its high computation efficiency and low storage cost.
We develop a novel Multiple hash cOdes jOint learNing method (MOON) for cross-media retrieval.
- Score: 30.77157852327981
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: In recent years, cross-media hashing technique has attracted increasing
attention for its high computation efficiency and low storage cost. However,
the existing approaches still have some limitations, which need to be explored.
1) A fixed hash length (e.g., 16bits or 32bits) is predefined before learning
the binary codes. Therefore, these models need to be retrained when the hash
length changes, that consumes additional computation power, reducing the
scalability in practical applications. 2) Existing cross-modal approaches only
explore the information in the original multimedia data to perform the hash
learning, without exploiting the semantic information contained in the learned
hash codes. To this end, we develop a novel Multiple hash cOdes jOint learNing
method (MOON) for cross-media retrieval. Specifically, the developed MOON
synchronously learns the hash codes with multiple lengths in a unified
framework. Besides, to enhance the underlying discrimination, we combine the
clues from the multimodal data, semantic labels and learned hash codes for hash
learning. As far as we know, the proposed MOON is the first work to
simultaneously learn different length hash codes without retraining in
cross-media retrieval. Experiments on several databases show that our MOON can
achieve promising performance, outperforming some recent competitive shallow
and deep methods.
Related papers
- Deep Lifelong Cross-modal Hashing [17.278818467305683]
We propose a novel deep lifelong cross-modal hashing to achieve lifelong hashing retrieval instead of re-training hash function repeatedly.
Specifically, we design lifelong learning strategy to update hash functions by directly training the incremental data instead of retraining new hash functions using all the accumulated data.
It yields substantial average over 20% in retrieval accuracy and almost reduces over 80% training time when new data arrives continuously.
arXiv Detail & Related papers (2023-04-26T07:56:22Z) - A Lower Bound of Hash Codes' Performance [122.88252443695492]
In this paper, we prove that inter-class distinctiveness and intra-class compactness among hash codes determine the lower bound of hash codes' performance.
We then propose a surrogate model to fully exploit the above objective by estimating the posterior of hash codes and controlling it, which results in a low-bias optimization.
By testing on a series of hash-models, we obtain performance improvements among all of them, with an up to $26.5%$ increase in mean Average Precision and an up to $20.5%$ increase in accuracy.
arXiv Detail & Related papers (2022-10-12T03:30:56Z) - Efficient Cross-Modal Retrieval via Deep Binary Hashing and Quantization [5.799838997511804]
Cross-modal retrieval aims to search for data with similar semantic meanings across different content modalities.
We propose a jointly learned deep hashing and quantization network (HQ) for cross-modal retrieval.
Experimental results on the NUS-WIDE, MIR-Flickr, and Amazon datasets demonstrate that HQ achieves boosts of more than 7% in precision.
arXiv Detail & Related papers (2022-02-15T22:00:04Z) - One Loss for All: Deep Hashing with a Single Cosine Similarity based
Learning Objective [86.48094395282546]
A deep hashing model typically has two main learning objectives: to make the learned binary hash codes discriminative and to minimize a quantization error.
We propose a novel deep hashing model with only a single learning objective.
Our model is highly effective, outperforming the state-of-the-art multi-loss hashing models on three large-scale instance retrieval benchmarks.
arXiv Detail & Related papers (2021-09-29T14:27:51Z) - Unsupervised Multi-Index Semantic Hashing [23.169142004594434]
We propose an unsupervised hashing model that learns hash codes that are both effective and highly efficient by being optimized for multi-index hashing.
We experimentally compare MISH to state-of-the-art semantic hashing baselines in the task of document similarity search.
We find that even though multi-index hashing also improves the efficiency of the baselines compared to a linear scan, they are still upwards of 33% slower than MISH.
arXiv Detail & Related papers (2021-03-26T13:33:48Z) - Deep Cross-modal Hashing via Margin-dynamic-softmax Loss [39.663995702994725]
We propose a novel cross-modal hashing method, called Deep Cross-modal Hashing via textitMargin-dynamic-softmax Loss (DCHML)
First, DCHML first trains a proxy hashing network to transform each category information of a dataset into a semantic discriminative hash code.
Next, without defining the similarity between datapoints to supervise the training process of the modality-specific hashing networks, we propose a novel textitmargin-dynamic-softmax loss
arXiv Detail & Related papers (2020-11-06T16:02:35Z) - 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) - Deep Reinforcement Learning with Label Embedding Reward for Supervised
Image Hashing [85.84690941656528]
We introduce a novel decision-making approach for deep supervised hashing.
We learn a deep Q-network with a novel label embedding reward defined by Bose-Chaudhuri-Hocquenghem codes.
Our approach outperforms state-of-the-art supervised hashing methods under various code lengths.
arXiv Detail & Related papers (2020-08-10T09:17:20Z) - 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) - A Survey on Deep Hashing Methods [52.326472103233854]
Nearest neighbor search aims to obtain the samples in the database with the smallest distances from them to the queries.
With the development of deep learning, deep hashing methods show more advantages than traditional methods.
Deep supervised hashing is categorized into pairwise methods, ranking-based methods, pointwise methods and quantization.
Deep unsupervised hashing is categorized into similarity reconstruction-based methods, pseudo-label-based methods and prediction-free self-supervised learning-based methods.
arXiv Detail & Related papers (2020-03-04T08:25:15Z) - A Novel Incremental Cross-Modal Hashing Approach [21.99741793652628]
We propose a novel incremental cross-modal hashing algorithm termed "iCMH"
The proposed approach consists of two sequential stages, namely, learning the hash codes and training the hash functions.
Experiments across a variety of cross-modal datasets and comparisons with state-of-the-art cross-modal algorithms shows the usefulness of our approach.
arXiv Detail & Related papers (2020-02-03T12:34:56Z)
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.