Search

In this paper, we conduct an extensive study on the use of pre-trained convolutional neural networks (CNNs) for omnidirectional image quality assessment (IQA). To cope with the lack of available IQA databases, transfer learning from seven pre-trained CNN models is investigated over retraining on standard 2D databases. In addition, we explore the influence of various image representations and training strategies on the model’s performance. A comparison of the use of projected versus radial content, and multichannel CNN versus patch-wise training is also covered. The experimental results on two publicly available databases are used to draw conclusions about which strategy best fits the visual quality prediction and at which computational cost. The analysis shows that retraining CNN models on 2D IQA databases improves the prediction accuracy. The latter and the required computational time are found to be significantly affected by the training strategy. Cross-database evaluations demonstrate that the nature and variety of the content impact the generalization ability of the models. Finally, we show that conclusions coming from other image processing communities may not hold for IQA. The provided discussion shall provide insights and recommendations when using pre-trained CNNs for omnidirectional IQA. [ABSTRACT FROM AUTHOR]

As two practical and important image processing tasks, color demosaicking (CDM) and super-resolution (SR) have been studied for decades. However, most literature studies these two tasks independently, ignoring the potential benefits of a joint solution. In this paper, aiming at efficient and effective joint demosaicking and super-resolution (JDSR), a well-designed two-stage convolutional neural network (CNN) architecture is proposed. For the first stage, by making use of the sampling-pattern information, a pattern-aware feature extraction (PFE) module extracts features directly from the Bayer-sampled low-resolution (LR) image, while keeping the resolution of the extracted features the same as the input. For the second stage, a dual-branch feature refinement (DFR) module effectively decomposes the features into two components with different spatial frequencies, on which different learning strategies are applied. On each branch of the DFR module, the feature refinement unit, namely, densely-connected dual-path enhancement blocks (DDEB), establishes a sophisticated nonlinear mapping from the LR space to the high-resolution (HR) space. To achieve strong representational power, two paths of transformations and the channel attention mechanism are adopted in DDEB. Extensive experiments demonstrate that the proposed method is superior to the sequential combination of state-of-the-art (SOTA) CDM and SR methods. Moreover, with much smaller model size, our approach also surpasses other SOTA JDSR methods. [ABSTRACT FROM AUTHOR]

Feature matching, which refers to identifying and then corresponding the same or similar visual pattern from two or more images, is a key technique in any image processing task that requires establishing good correspondences between images. Given potential correspondences (matches) in two scenes, a novel whole-part deep learning framework, termed as Context Structure Representation Network (CSR-Net), is designed to infer the probabilities of arbitrary correspondences being inliers. Traditional approaches commonly build the local relation between correspondences by manually engineered criteria. Different from existing attempts, the main idea of our work is to learn explicitly neighborhood structure of each correspondence, allowing us to formulate the matching problem into a dynamic local structure consensus evaluation in an end-to-end fashion. For this purpose, we propose a permutation-invariant STructure Representation (STR) learning module, which can easily merge different types of networks into a unified architecture to deal with sparse matches directly. By the collaborative use of STR, we introduce a Context-Aware Attention (CAA) mechanism to adaptively re-calibrate structure features via a rotation-invariant context aware encoding and simple feature gating, thus arising the ability of fine-grained patterns recognition. Moreover, to further weaken the cost of establishing reliable correspondences, the CSR-Net is formulated as whole-part consensus learning, where the aim of whole level is compensating rigid transformations. In order to demonstrate our CSR-Net can effectively boost the baselines, we intensively experiment on image matching and other visual tasks. The results of the experiment confirm that the matching performances of CSR-Net have significantly improved over nine state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Missing data reconstruction is a classical, yet challenging problem in remote sensing (RS) image processing due to the complex atmospheric environment and variability of satellite sensors. Most of the contemporary reconstruction methods either handle only one specific task or require supplementary data, while the single input for multitask reconstruction has not been explored yet. In this article, we propose a novel generative adversarial network-based unified framework for missing RS image reconstruction, which is capable of various reconstruction tasks given only single-source data as input. Specifically, we first propose a mask extraction network (MEN) to obtain a united soft mask, which represents the intrinsic prior under various scenarios and indicates not only location, but also context information. The versatility of mask extraction enables the multitask reconstruction of RS images. Besides, we propose a unified inpainting network (UIN) to repair diverse degraded images. Being specifically tailored for RS images, dilated pyramidal convolutions (DPCs) and an attention fusion mechanism (AFM) are introduced to further improve the feature extraction ability and thus exhaustly leveraging the single-input information. Extensive experiments demonstrate the uncompromising performance of the proposed method against state-of-the-art multiinput methods on diverse missing restoration. Moreover, further exploration shows the potential of the proposed method to utilize joint spatial–spectral–temporal information, which is evaluated to outperform existing competitors on remote sense images. [ABSTRACT FROM AUTHOR]

In general, image restoration involves mapping from low-quality images to their high-quality counterparts. Such optimal mapping is usually nonlinear and learnable by machine learning. Recently, deep convolutional neural networks have proven promising for such learning processing. It is desirable for an image processing network to support well with three vital tasks, namely: 1) super-resolution; 2) denoising; and 3) deblocking. It is commonly recognized that these tasks have strong correlations, which enable us to design a general framework to support all tasks. In particular, the selection of feature scales is known to significantly impact the performance on these tasks. To this end, we propose the cross-scale residual network to exploit scale-related features among the three tasks. The proposed network can extract spatial features across different scales and establish cross-temporal feature reusage, so as to handle different tasks in a general framework. Our experiments show that the proposed approach outperforms state-of-the-art methods in both quantitative and qualitative evaluations for multiple image restoration tasks. [ABSTRACT FROM AUTHOR]

Cloud and cloud shadow segmentation is one of the most important issues in remote sensing image processing. Most of the remote sensing images are very complicated. In this work, a dual-branch model composed of transformer and convolution network is proposed to extract semantic and spatial detail information of the image, respectively, to solve the problems of false detection and missed detection. To improve the model’s feature extraction, a mutual guidance module (MGM) is introduced, so that the transformer branch and the convolution branch can guide each other for feature mining. Finally, in view of the problem of rough segmentation boundary, this work uses different features extracted by the transformer branch and the convolution branch for decoding and repairs the rough segmentation boundary in the decoding part to make the segmentation boundary clearer. Experimental results on the Landsat-8, Sentinel-2 data, the public dataset high-resolution cloud cover validation dataset created by researchers at Wuhan University (HRC_WHU), and the public dataset Spatial Procedures for Automated Removal of Cloud and Shadow (SPARCS) demonstrate the effectiveness of our method and its superiority to the existing state-of-the-art cloud and cloud shadow segmentation approaches. [ABSTRACT FROM AUTHOR]

Retrieving 3D shapes based on 2D images is a challenging research topic, due to the significant gap between different domains. Recently, various approaches have been proposed to handle this problem. However, the majority of methods target the cross-domain retrieval task as a pure domain adaptation problem, which focuses on the alignment but ignores the visual relevance between the 2D images and their corresponding 3D shapes. To fundamentally decrease the divergence between different domains, we propose a novel cross-domain learning network (CLN) for 2D image-based 3D shape retrieval task. First, we estimate the pose information from the 2D image to guide the view rendering of 3D shapes, which increases the visual correlations of the cross-domain data to eliminate the divergence between them. Second, we introduce a novel joint learning network, considering both the domain-specific characteristics and the cross-domain interactions for data alignment, which further compensates for the gap between different domains by controlling the distance of intra- and inter-classes. After the metric learning process, discriminative descriptors of images and shapes are generated for the cross-domain retrieval task. To prove the effectiveness and robustness of the proposed method, we conduct extensive experiments on the MI3DOR, SHREC’13, and SHREC’14 datasets. The experimental results demonstrate the superiority of our proposed method, and significant improvements have been achieved compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Feature matching, which aims to seek good correspondences from an image pair of the same or similar scene, is one of the important studies on digital remote sensing (RS) image processing. However, alongside the common degradation problems, such as geometric distortion, RS images also often face nonlinear radiation distortions, thereby posing more complex matching patterns. To reduce the cost of establishing reliable correspondences, this article proposes a simple, but effective end-to-end hierarchical learning framework, termed interactive generative structure learning network (IGS-Net). The key thinking of our approach is to offer a structure self-generate learning mechanism, called interactive generative structure learning (IGSL) block, for modeling the local context information of potential correspondences. Specifically, IGSL contains two novel operations: adaptive structure-aware representation (ASR) and physical constraint embedding. Besides, we introduce a coarse-to-fine geometry estimation pipeline aligning two sets of feature points to weaken the degree of randomness in matching patterns, thus improving the generalization ability of representation learning. Overall, this differentiable representation learning architecture can be inserted into existing classification models easily for robust outlier detection and removal. In order to demonstrate that our IGS-Net can boost the baselines, we intensively experiment on both single modality and multimodal RS image datasets. The large amounts of experiment results reveal that the matching performances of IGS-Net are significantly improved over eight state-of-the-art competitors. [ABSTRACT FROM AUTHOR]

Deep convolutional neural networks (CNNs) have emerged as a new paradigm for Mammogram diagnosis. Contemporary CNN-based computer-aided-diagnosis systems (CADs) for breast cancer directly extract latent features from input mammogram image and ignore the importance of morphological features. In this paper, we introduce a novel end-to-end deep learning framework for mammogram image processing, which computes mass segmentation and simultaneously predicts diagnosis results. Specifically, our method is constructed in a dual-path architecture that solves the mapping in a dual-problem manner, with an additional consideration of important shape and boundary knowledge. One path, called the Locality Preserving Learner (LPL), is devoted to hierarchically extracting and exploiting intrinsic features of the input. Whereas the other path, called the Conditional Graph Learner (CGL), focuses on generating geometrical features via modeling pixel-wise image to mask correlations. By integrating the two learners, both the cancer semantics and cancer representations are well learned, and the component learning paths in return complement each other, contributing an improvement to the mass segmentation and cancer classification problem at the same time. In addition, by integrating an automatic detection set-up, the DualCoreNet achieves fully automatic breast cancer diagnosis practically. Experimental results show that in benchmark DDSM dataset, DualCoreNet has outperformed other related works in both segmentation and classification tasks, achieving 92.27% DI coefficient and 0.85 AUC score. In another benchmark INbreast dataset, DualCoreNet achieves the best mammography segmentation (93.69% DI coefficient) and competitive classification performance (0.93 AUC score). [ABSTRACT FROM AUTHOR]

Object detection from remote sensing images (RSIs) is a basic topic in the area of aviation and satellite image processing, which has great effects on geological disaster detection, agricultural planning, and land utilization. However, it is always faced with several severe difficulties. For instance, the scale of the target spans over a very wide range, and the difference between the target size and the image size is huge, as some targets only account for a dozen pixels compared with the RSI of the megapixel level. In this work, an innovative object detection network (GLNet) is proposed for remote sensing imagery. Our approach integrates global context clues extracted by the multiscale perception (MSP) module and local spatial contextual correlations encoded by Clip long short-term memory (Clip-LSTM). These rich semantic features are further exploited to design a self-adapted anchor (SA) module to alleviate the scale variations in RSIs. Extensive experiments are executed on several public easily accessed benchmarks, including DOTA, NWPU VHR-10, and DIOR. Experimental results have demonstrated that our GLNet outperforms numerous latest methods. [ABSTRACT FROM AUTHOR]

Medical image processing is one of the most important topics in the Internet of Medical Things (IoMT). Recently, deep learning methods have carried out state-of-the-art performances on medical imaging tasks. In this paper, we propose a novel transfer learning framework for medical image classification. Moreover, we apply our method COVID-19 diagnosis with lung Computed Tomography (CT) images. However, well-labeled training data sets cannot be easily accessed due to the disease's novelty and privacy policies. The proposed method has two components: reduced-size Unet Segmentation model and Distant Feature Fusion (DFF) classification model. This study is related to a not well-investigated but important transfer learning problem, termed Distant Domain Transfer Learning (DDTL). In this study, we develop a DDTL model for COVID-19 diagnosis using unlabeled Office-31, Caltech-256, and chest X-ray image data sets as the source data, and a small set of labeled COVID-19 lung CT as the target data. The main contributions of this study are: 1) the proposed method benefits from unlabeled data in distant domains which can be easily accessed, 2) it can effectively handle the distribution shift between the training data and the testing data, 3) it has achieved 96% classification accuracy, which is 13% higher classification accuracy than “non-transfer” algorithms, and 8% higher than existing transfer and distant transfer algorithms. [ABSTRACT FROM AUTHOR]