Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling

Xue, Shan; Li, Pingping; Gou, Guixia; Zhou, Qiuzhan; Wang, Zhen

doi:10.3390/rs12172789

Cited by 16 publications

(7 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…By optimizing (14), the generators can generate modalityinvariant representations of features and hash codes, when the boundaries between different modalities disappear, it's much easier to achieve a precise retrieval.…”

Section: Deep Adversarial Network For Modality Confusingmentioning

confidence: 99%

“…Take the widely-used unimodal RS dataset UC-Merced for example, Song et al [13] used a deep hashing convolutional neural network (DHCNN) for retrieval and classification and achieve a mean average precision(MAP) of 98.08% on UC-Merced. recent research [14] carried out retrieval experiments on UC-Merced and the MAP@20 even reached to 99.7%. In other words, we can get almost everything we want from huge databases accurately.…”

Section: Introductionmentioning

confidence: 98%

See 1 more Smart Citation

Deep Adversarial Cascaded Hashing for Cross-Modal Vessel Image Retrieval

Guo¹,

Guan²

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

In recent years, cross-modal remote sensing image retrieval(CMRSIR) has attracted a lot of attention in remote sensing(RS) information processing. It's worth mentioning that land cover scenes, whether unimodal or cross-modal, are the primary research contents of remote sensing image retrieval (RSIR), and there are few studies on vessel images captured by RS satellites, let alone cross-modal retrieval tasks. Vessel images have smaller scale, lower resolution, and less detailed information than land cover images, so it's difficult to retrieve the exact images we want. In this paper, a hashing method called deep adversarial cascaded hashing (DACH) is proposed to address these problems. To extract the subtle and discriminative features contained in RS vessel images accurately, we build a deep cascaded network that fuses multilevel features boosted both in depth and width, and the self-attention mechanism can further enhance the fused features. Combined with hash learning, we also design a weighted quintuplet loss to supervise the transition of discrimination and similarity between different metric spaces, and reduce crossmodal discrepancy at the same time. In addition, we apply the deep adversarial constraint to both feature learning and hash learning, trying to bridge the modality gap and achieve a cross-modal retrieval as precise as unimodal retrieval. Comprehensive experiments on two public bimodal vessel image datasets compared with several excellent cross-modal retrieval methods are conducted to demonstrate the effectiveness of our DACH, and the results show that the proposed method is effective and competitive on cross-modal vessel image retrieval tasks, outperforming state-of-the-art methods.

show abstract

Section: Deep Adversarial Network For Modality Confusingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 98%

Deep Adversarial Cascaded Hashing for Cross-Modal Vessel Image Retrieval

Guo¹,

Guan²

2023

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…Then, two multi-layer networks were constructed to regularize the above vectors. In [30], Shan et al proposed hard probability sampling hash retrieval method to improve retrieval performance. In [31], Liu et al adopted a deep feature learning model and an adversarial hash learning model to extract dense features of images and map the dense features onto the compact hash codes, respectively.…”

Section: B Deep Hashing In Rsirmentioning

confidence: 99%

“…In addition, a cohesion intensive deep hashing model was developed for RSIR, where the cohesiveness of image hash codes within one class was intensified via a weighted loss strategy [29]. In [30], Shan et al combined hash code learning with hard probability sampling in a deep network to improve retrieval performance. In [31], a feature and hash (FAH) learning method, which consists of a deep feature learning model and an adversarial hash learning model, was proposed for RSIR.…”

mentioning

confidence: 99%

Asymmetric Hash Code Learning for Remote Sensing Image Retrieval

Song,

Gao,

Dian

et al. 2022

Preprint

View full text Add to dashboard Cite

Remote sensing image retrieval (RSIR), aiming at searching for a set of similar items to a given query image, is a very important task in remote sensing applications. Deep hashing learning as the current mainstream method has achieved satisfactory retrieval performance. On one hand, various deep neural networks are used to extract semantic features of remote sensing images. On the other hand, the hashing techniques are subsequently adopted to map the high-dimensional deep features to the low-dimensional binary codes. This kind of methods attempts to learn one hash function for both the query and database samples in a symmetric way. However, with the number of database samples increasing, it is typically timeconsuming to generate the hash codes of large-scale database images. In this paper, we propose a novel deep hashing method, named asymmetric hash code learning (AHCL), for RSIR. The proposed AHCL generates the hash codes of query and database images in an asymmetric way. In more detail, the hash codes of query images are obtained by binarizing the output of the network, while the hash codes of database images are directly learned by solving the designed objective function. In addition, we combine the semantic information of each image and the similarity information of pairs of images as supervised information to train a deep hashing network, which improves the representation ability of deep features and hash codes. The experimental results on three public datasets demonstrate that the proposed method outperforms symmetric methods in terms of retrieval accuracy and efficiency. The source code is available at https://github.com/weiweisong415/Demo AHCL for TGRS2022.

show abstract

“…In single-modal retrieval, both query data and archived data are RS images, and existing research methods are mostly concentrated on CBIR [9], whose accuracy has been promoted tremendously, owing to the application and development of deep metric learning over the past few years [10][11][12][13]. At the same time, the application of the deep Hash method has made large-scale RS image retrieval possible [14][15][16][17]. While single-modal retrieval has achieved enormous progress, it has natural weaknesses in retrieval flexibility and semantic richness.…”

Section: Introductionmentioning

confidence: 99%

A Cross-Attention Mechanism Based on Regional-Level Semantic Features of Images for Cross-Modal Text-Image Retrieval in Remote Sensing

Zheng

Wang

et al. 2022

Applied Sciences

View full text Add to dashboard Cite

With the rapid development of remote sensing (RS) observation technology over recent years, the high-level semantic association-based cross-modal retrieval of RS images has drawn some attention. However, few existing studies on cross-modal retrieval of RS images have addressed the issue of mutual interference between semantic features of images caused by “multi-scene semantics”. Therefore, we proposed a novel cross-attention (CA) model, called CABIR, based on regional-level semantic features of RS images for cross-modal text-image retrieval. This technique utilizes the CA mechanism to implement cross-modal information interaction and guides the network with textual semantics to allocate weights and filter redundant features for image regions, reducing the effect of irrelevant scene semantics on retrieval. Furthermore, we proposed BERT plus Bi-GRU, a new approach to generating statement-level textual features, and designed an effective temperature control function to steer the CA network toward smooth running. Our experiment suggested that CABIR not only outperforms other state-of-the-art cross-modal image retrieval methods but also demonstrates high generalization ability and stability, with an average recall rate of up to 18.12%, 48.30%, and 55.53% over the datasets RSICD, UCM, and Sydney, respectively. The model proposed in this paper will be able to provide a possible solution to the problem of mutual interference of RS images with “multi-scene semantics” due to complex terrain objects.

show abstract

Deep Hash Remote Sensing Image Retrieval with Hard Probability Sampling

Cited by 16 publications

References 44 publications

Deep Adversarial Cascaded Hashing for Cross-Modal Vessel Image Retrieval

Deep Adversarial Cascaded Hashing for Cross-Modal Vessel Image Retrieval

Asymmetric Hash Code Learning for Remote Sensing Image Retrieval

A Cross-Attention Mechanism Based on Regional-Level Semantic Features of Images for Cross-Modal Text-Image Retrieval in Remote Sensing

Contact Info

Product

Resources

About