Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval

@article{Sumbul2021InformativeAR,
  title={Informative and Representative Triplet Selection for Multilabel Remote Sensing Image Retrieval},
  author={Gencer Sumbul and Mahdyar Ravanbakhsh and Beg{\"u}m Demir},
  journal={IEEE Transactions on Geoscience and Remote Sensing},
  year={2021},
  volume={60},
  pages={1-11}
}
Learning the similarity between remote sensing (RS) images forms the foundation for content-based RS image retrieval (CBIR). Recently, deep metric learning approaches that map the semantic similarity of images into an embedding (metric) space have been found very popular in RS. A common approach for learning the metric space relies on the selection of triplets of similar (positive) and dissimilar (negative) images to a reference image called an anchor. Choosing triplets is a difficult task… 
[PDF] Semantic Reader
7 Citations
Background Citations
1
Methods Citations
2

7 Citations

Multisource Data Reconstruction-Based Deep Unsupervised Hashing for Unisource Remote Sensing Image Retrieval

A new Multisource data reconstruction-based deep unsupervised Hashing method, called MrHash, which explores the characteristics of RS images to construct reliable pseudolabels and proposes a novel multisemantic hash loss by using the Kullback–Leibler (KL) divergence to preserve the semantic similarity of these pseudo-multilabels in Hamming space.

Remote Sensing Image Retrieval in the Past Decade: Achievements, Challenges, and Future Directions

This article provides a systematic survey of the recently published RSIR methods and benchmarks by reviewing more than 200 papers and demonstrates that deep learning-based methods are currently the dominant RSIR approaches and outperform handcrafted feature- based methods by a significant margin.

Deep Unsupervised Contrastive Hashing for Large-Scale Cross-Modal Text-Image Retrieval in Remote Sensing

Experimental results show that the proposed DUCH outperforms state-of-the-art unsupervised cross- modal hashing methods on two multi-modal (image and text) benchmark archives in RS.

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

This work proposed a novel cross-attention (CA) model, called CABIR, based on regional-level semantic features of RS images for cross-modal text-image retrieval, and 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.

Benchmarking and scaling of deep learning models for land cover image classification

Triplet Loss-less Center Loss Sampling Strategies in Facial Expression Recognition Scenarios

A selective attention module is introduced that provides a combination of pixel-wise and element-wise attention coefficients using high-semantic deep features of input samples to achieve better results in negative sample selection strategies.

Multimorbidity Content-Based Medical Image Retrieval Using Proxies

A novel multi-label metric learning method that can be used for both classification and content- based image retrieval and is able to support diagnosis by predicting the presence of diseases and provide evidence for these predictions by returning samples with similar pathological content to the user.

References

SHOWING 1-10 OF 41 REFERENCES

Enhancing remote sensing image retrieval using a triplet deep metric learning network

  • Rui CaoQian Zhang G. Qiu
  • Computer Science, Environmental Science
    International Journal of Remote Sensing
  • 2019
A novel content-based remote sensing image retrieval (RSIR) method based on Triplet deep metric learning convolutional neural network (CNN) that significantly outperforms state-of-the-art methods.

Multilabel Remote Sensing Image Retrieval Using a Semisupervised Graph-Theoretic Method

A semisupervised graph-theoretic method in the framework of multilabel RS image retrieval problems that retrieves images similar to a given query image by a subgraph matching strategy and shows effectiveness when compared with the state-of-the-art RS content-based image retrieval methods.

Deep Learning for Multilabel Remote Sensing Image Annotation With Dual-Level Semantic Concepts

An end-to-end deep learning framework for object-level multilabel annotation of RS images and adopts the binary cross-entropy loss for classification and the triplet loss for image embedding learning is proposed.

Unsupervised Deep Feature Learning for Remote Sensing Image Retrieval

This paper focuses on developing an effective feature learning method for RSIR, and proposes the deep convolutional auto-encoder (DCAE) model to deeply learn the discriminative descriptor for the RS image.

A Triplet Nonlocal Neural Network With Dual-Anchor Triplet Loss for High-Resolution Remote Sensing Image Retrieval

This article constructs a triplet nonlocal neural network (T-NLNN) model that combines deep metric learning and nonlocal operation, and proposes a dual-anchor triplet loss function to facilitate the utilization of information in the input samples.

Deep Learning for Image Search and Retrieval in Large Remote Sensing Archives

This chapter presents recent advances in content based image search and retrieval (CBIR) systems in remote sensing (RS) for fast and accurate information discovery from massive data archives and presents the deep hashing based CBIR systems that have high time-efficient search capability within huge data archives.

Metric-Learning-Based Deep Hashing Network for Content-Based Retrieval of Remote Sensing Images

A metric-learning-based hashing network is introduced, which implicitly uses a big, pretrained DNN as an intermediate representation step without the need of retraining or fine-tuning and learns a semantic-based metric space where the features are optimized for the target retrieval task.

Deep Metric Learning Beyond Binary Supervision

A new triplet loss is proposed that allows distance ratios in the label space to be preserved in the learned metric space and enables the model to learn the degree of similarity rather than just the order.

Aggregated Deep Local Features for Remote Sensing Image Retrieval

This paper presents an image retrieval pipeline that uses attentive, local convolutional features and aggregates them using the Vector of Locally Aggregated Descriptors (VLAD) to produce a global descriptor.

BigEarthNet-MM: A Large-Scale, Multimodal, Multilabel Benchmark Archive for Remote Sensing Image Classification and Retrieval [Software and Data Sets]

The multi-modal BigEarthNet (BigEarthNet-MM) benchmark archive made up of 590,326 pairs of Sentinel-1 and Sentinel-2 image patches is presented to support the deep learning studies in multi- modal multi-label remote sensing image retrieval and classification.