Medical image segmentation is an important part of medical image analysis. With the rapid development of convolutional neural networks in image processing, deep learning methods have achieved great success in the field of medical image processing. Deep learning is also used in the field of auxiliary diagnosis of glaucoma, and the effective segmentation of the optic disc area plays an important assistant role in the diagnosis of doctors in the clinical diagnosis of glaucoma. Previously, many U-Net-based optic disc segmentation methods have been proposed. However, the channel dependence of different levels of features is ignored. The performance of fundus image segmentation in small areas is not satisfactory. In this paper, we propose a new aggregation channel attention network to make full use of the influence of context information on semantic segmentation. Different from the existing attention mechanism, we exploit channel dependencies and integrate information of different scales into the attention mechanism. At the same time, we improved the basic classification framework based on cross entropy, combined the dice coefficient and cross entropy, and balanced the contribution of dice coefficients and cross entropy loss to the segmentation task, which enhanced the performance of the network in small area segmentation. The network retains more image features, restores the significant features more accurately, and further improves the segmentation performance of medical images. We apply it to the fundus optic disc segmentation task. We demonstrate the segmentation performance of the model on the Messidor dataset and the RIM-ONE dataset, and evaluate the proposed architecture. Experimental results show that our network architecture improves the prediction performance of the base architectures under different datasets while maintaining the computational efficiency. The results render that the proposed technologies improve the segmentation with 0.0469 overlapping error on Messidor.

In the Fourier frequency domain, luminance information is primarily encoded in the amplitude component, while spatial structure information is significantly contained within the phase component. Existing low-light image enhancement techniques using Fourier transform have mainly focused on amplifying the amplitude component and simply replicating the phase component, an approach that often leads to color distortions and noise issues. In this paper, we propose a Dual-Stage Multi-Branch Fourier Low-Light Image Enhancement (DMFourLLIE) framework to address these limitations by emphasizing the phase component's role in preserving image structure and detail. The first stage integrates structural information from infrared images to enhance the phase component and employs a luminance-attention mechanism in the luminance-chrominance color space to precisely control amplitude enhancement. The second stage combines multi-scale and Fourier convolutional branches for robust image reconstruction, effectively recovering spatial structures and textures. This dual-branch joint optimization process ensures that complex image information is retained, overcoming the limitations of previous methods that neglected the interplay between amplitude and phase. Extensive experiments across multiple datasets demonstrate that DMFourLLIE outperforms current state-of-the-art methods in low-light image enhancement.

A rich line of works focus on designing elegant loss functions under the deep metric learning (DML) paradigm to learn a discriminative embedding space for remote sensing image retrieval (RSIR). Essentially, such embedding space could efficiently distinguish deep feature descriptors. So far, most existing losses used in RSIR are based on triplets, which have disadvantages of local optimization, slow convergence and insufficient use of similarity structure in a mini-batch. In this paper, we present a novel DML method named as global optimal structured loss to deal with the limitation of triplet loss. To be specific, we use a softmax function rather than a hinge function in our novel loss to realize global optimization. In addition, we present a novel optimal structured loss, which globally learn an efficient deep embedding space with mined informative sample pairs to force the positive pairs within a limitation and push the negative ones far away from a given boundary. We have conducted extensive experiments on four public remote sensing datasets and the results show that the proposed global optimal structured loss with pairs mining scheme achieves the state-of-the-art performance compared with the baselines.

With the improvement of various space-satellite shooting methods, the sources, scenes, and quantities of remote sensing data are also increasing. An effective and fast remote sensing image retrieval method is necessary, and many researchers have conducted a lot of work in this direction. Nevertheless, a fast retrieval method called hashing retrieval is proposed to improve retrieval speed, while maintaining retrieval accuracy and greatly reducing memory space consumption. At the same time, proxy-based metric learning losses can reduce convergence time. Naturally, we present a proxy-based hash retrieval method, called DHPL (Deep Hashing using Proxy Loss), which combines hash code learning with proxy-based metric learning in a convolutional neural network. Specifically, we designed a novel proxy metric learning network, and we used one hash loss function to reduce the quantified losses. For the University of California Merced (UCMD) dataset, DHPL resulted in a mean average precision (mAP) of up to 98.53% on 16 hash bits, 98.83% on 32 hash bits, 99.01% on 48 hash bits, and 99.21% on 64 hash bits. For the aerial image dataset (AID), DHPL achieved an mAP of up to 93.53% on 16 hash bits, 97.36% on 32 hash bits, 98.28% on 48 hash bits, and 98.54% on 64 bits. Our experimental results on UCMD and AID datasets illustrate that DHPL could generate great results compared with other state-of-the-art hash approaches.

As satellite observation technology improves, the number of remote sensing images significantly and rapidly increases. Therefore, a growing number of studies are focusing on remote sensing image retrieval. However, having a large number of remote sensing images considerably slows the retrieval time and takes up a great deal of memory space. The hash method is being increasingly used for rapid image retrieval because of its remarkably fast performance. At the same time, selecting samples that contain more information and greater stability to train the network has gradually become the key to improving retrieval performance. Given the above considerations, we propose a deep hash remote sensing image retrieval method, called the hard probability sampling hash retrieval method (HPSH), which combines hash code learning with hard probability sampling in a deep network. Specifically, we used a probability sampling method to select training samples, and we designed one novel hash loss function to better train the network parameters and reduce the hashing accuracy loss due to quantization. Our experimental results demonstrate that HPSH could yield an excellent representation compared with other state-of-the-art hash approaches. For the university of California, merced (UCMD) dataset, HPSH+S resulted in a mean average precision (mAP) of up to 90.9% on 16 hash bits, 92.2% on 24 hash bits, and 92.8% on 32 hash bits. For the aerial image dataset (AID), HPSH+S achieved a mAP of up to 89.8% on 16 hash bits, 93.6% on 24 hash bits, and 95.5% on 32 hash bits. For the UCMD dataset, with the use of data augmentation, our proposed approach achieved a mAP of up to 99.6% on 32 hash bits and 99.7% on 64 hash bits.

Diabetic retinopathy (DR) is a common complication of diabetes mellitus (DM), and it is necessary to diagnose DR in the early stages of treatment. With the rapid development of convolutional neural networks in the field of image processing, deep learning methods have achieved great success in the field of medical image processing. Various medical lesion detection systems have been proposed to detect fundus lesions. At present, in the image classification process of diabetic retinopathy, the fine-grained properties of the diseased image are ignored and most of the retinopathy image data sets have serious uneven distribution problems, which limits the ability of the network to predict the classification of lesions to a large extent. We propose a new non-homologous bilinear pooling convolutional neural network model and combine it with the attention mechanism to further improve the network’s ability to extract specific features of the image. The experimental results show that, compared with the most popular fundus image classification models, the network model we proposed can greatly improve the prediction accuracy of the network while maintaining computational efficiency.