Search

In recent years, many deep learning-based object detection methods have performed well in various applications, especially in large-scale object detection. However, when detecting small targets, previous object detection algorithms cannot achieve good results due to the characteristics of the small targets themselves. To address the aforementioned issues, we propose the small object algorithm model MCF-YOLOv5, which has undergone three improvements based on YOLOv5. Firstly, a data augmentation strategy combining Mixup and Mosaic is used to increase the number of small targets in the image and reduce the interference of noise and changes in detection. Secondly, in order to accurately locate the position of small targets and reduce the impact of unimportant information on small targets in the image, the attention mechanism coordinate attention is introduced in YOLOv5's neck network. Finally, we improve the Feature Pyramid Network (FPN) structure and add a small object detection layer to enhance the feature extraction ability of small objects and improve the detection accuracy of small objects. The experimental results show that, with a small increase in computational complexity, the proposed MCF-YOLOv5 achieves better performance than the baseline on both the VisDrone2021 dataset and the Tsinghua Tencent100K dataset. Compared with YOLOv5, MCF-YOLOv5 has improved detection APsmall by 3.3% and 3.6%, respectively. [ABSTRACT FROM AUTHOR]

Object detection in remote sensing images (RSIs) poses great difficulties due to arbitrary orientations, various scales, and dense location of the targets over the ground. Recent evidence suggests that encoding the orientation information is of great use for training an accurate object detector for oriented object detection (OOD). In this article, we propose a new frequency-domain orientation learning (FDOL) module with two main components: the frequency-domain feature extraction (FFE) network and an orientation enhanced self-attention layer (OES-Layer). The FFE network models the interactions among spatial locations in the frequency domain to determine the frequency of spatial features. Then, these features are fed into our OES-Layer to learn the orientation information. Moreover, the orientation weights are adopted to guide the feature selection in a self-attention (SA) architecture, using them as a control gate to emphasize the spatial responses of target instances. Considering that the original similarity weights (calculated by the SA algorithm) do not distinctly model the orientation variation, the considered orientation weights provide an efficient asset to emphasize the orientation of objects. Extensive experiments on the DOTA and HRSC2016 datasets demonstrate that our method achieves state-of-the-art performance among single-scale methods while achieving competitive performance over multiscale methods. [ABSTRACT FROM AUTHOR]

Recently, deep learning has drawn significant attention in hyperspectral image (HSI) classification. With the growth of network depth and feature integration, deep learning demands abundant labeled samples to optimize many parameters. Unfortunately, most hyperspectral data are unlabeled and the available labeled samples are extremely limited. How to obtain richer features under limited training samples is a challenge for HSI classification. To tackle this issue, a new supervised multiscale alternately updated clique network (MSCN) is proposed for HSI classification to fully employ HSI features in different scales. Based on the Clique Block, we design the multiscale alternately updated clique block (MSCB) that applies convolution kernels of various sizes to adaptively exploit the multiscale HSI information and merge them within the block. Meanwhile, the recurrent feedback architecture is introduced to reuse high-level visual information and network parameters. The proposed MSCN includes two MSCBs to capture the multiscale spectral and spatial information in turn. The MSCN improves the information flow and the efficiency of parameter tuning through the feedback mechanism and the cross-utilization of multiscale feature. It not only obtains more abstract HSI information, but also reduces the network depth and the number of parameters, thereby improving the classification accuracy under limited samples. To certify the validity of the proposed MSCN, experiments are conducted on three real HSI datasets and compared with multiple state-of-the-art deep learning-based approaches. The experimental results demonstrate that the presented multiscale network achieves superior performance, especially in the case of a small number of training samples. [ABSTRACT FROM AUTHOR]

Recently, the graph convolutional network (GCN) has drawn increasing attention in the hyperspectral image (HSI) classification. Compared with the convolutional neural network (CNN) with fixed square kernels, GCN can explicitly utilize the correlation between adjacent land covers and conduct flexible convolution on arbitrarily irregular image regions; hence, the HSI spatial contextual structure can be better modeled. However, to reduce the computational complexity and promote the semantic structure learning of land covers, GCN usually works on superpixel-based nodes rather than pixel-based nodes; thus, the pixel-level spectral–spatial features cannot be captured. To fully leverage the advantages of the CNN and GCN, we propose a heterogeneous deep network called CNN-enhanced GCN (CEGCN), in which CNN and GCN branches perform feature learning on small-scale regular regions and large-scale irregular regions, and generate complementary spectral–spatial features at pixel and superpixel levels, respectively. To alleviate the structural incompatibility of the data representation between the Euclidean data-oriented CNN and non-Euclidean data-oriented GCN, we propose the graph encoder and decoder to propagate features between image pixels and graph nodes, thus enabling the CNN and GCN to collaborate in a single network. In contrast to other GCN-based methods that encode HSI into a graph during preprocessing, we integrate the graph encoding process into the network and learn edge weights from training data, which can promote the node feature learning and make the graph more adaptive to HSI content. Extensive experiments on three data sets demonstrate that the proposed CEGCN is both qualitatively and quantitatively competitive compared with other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep Convolutional Neural Networks (CNN) have drawn great attention in image super-resolution (SR). Recently, visual attention mechanism, which exploits both of the feature importance and contextual cues, has been introduced to image SR and proves to be effective to improve CNN-based SR performance. In this paper, we make a thorough investigation on the attention mechanisms in a SR model and shed light on how simple and effective improvements on these ideas improve the state-of-the-arts. We further propose a unified approach called “multi-grained attention networks (MGAN)” which fully exploits the advantages of multi-scale and attention mechanisms in SR tasks. In our method, the importance of each neuron is computed according to its surrounding regions in a multi-grained fashion and then is used to adaptively re-scale the feature responses. More importantly, the “channel attention” and “spatial attention” strategies in previous methods can be essentially considered as two special cases of our method. We also introduce multi-scale dense connections to extract the image features at multiple scales and capture the features of different layers through dense skip connections. Ablation studies on benchmark datasets demonstrate the effectiveness of our method. In comparison with other state-of-the-art SR methods, our method shows the superiority in terms of both accuracy and model size. [ABSTRACT FROM AUTHOR]

A spatial–spectral residual dense network-based compressive hyperspectral image (HSI) reconstruction method is proposed in this letter. The proposed method contains two networks: residual dense network for hyperspectral image reconstruction (RDNHIR) and spectral difference reconstruction network (SDRN). The RDNHIR network can extract the local features and global hierarchical features by cascading features of all residual dense blocks (RDBs). Then, SDRN takes full advantage of the strong correlation between spectral adjacent bands to better preserve the spectral feature of HSI. Finally, the adjacent spectral difference regularization is introduced into the loss function to further improve the performance. The experimental results show that the proposed method has better reconstruction quality than other state-of-the-art reconstruction methods, especially in the spectral domain. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification is an important technology for hyperspectral data analysis, which has the challenge of high dimensionality and limited training samples. Moreover, due to the spatial continuity of material distribution, it is reasonable to improve the performance of HSI classification from the local similarity viewpoint, i.e., pixels in the same local region have a high probability to share similar features. Therefore, in this paper, a novel method based on local similarity and kernel low-rank representation is proposed to improve the classification accuracy for HSI. First, taking into consideration that pixels in the same homogeneous region share similar spectral features (termed local similarity), the HSI is segmented by the superpixel segmentation algorithm to obtain the homogeneous regions. Then, a model of kernel low-rank representation based on local similarity (KLRRLS) is proposed for HSI classification. In the model of KLRRLS, the nonlinear structure characteristics of HSI are extracted by employing the kernel trick, and the low-rank constraint is used as a prior to restrict the recovery coefficient matrix in each segmentation region, thus efficiently solving the linear non-separable problem and exploiting the contextual information of HSI. Finally, the classification results are generated by fusing the result of each segmented map via the maximum voting mechanism. Experimental results on three real HSI datasets demonstrate that the proposed method can effectively improve the classification accuracy. [ABSTRACT FROM AUTHOR]

Spatial rich model (SRM) steganalysis feature is formed by high-order statistics collected from image noise residuals. These statistics are simply rescaled before machine learning. It is noted that SRM features of different cover images are very different. In this paper, we propose a feature normalization method based on random feature-subsets (NRS) for SRM. We randomly draw feature-subsets from SRM feature. Then these feature-subsets are normalized by using per-sample rescaling method to make the feature-subsets of different images have the same 1-norm (the sum of all elements). The proposed NRS method can adjust the feature distribution and increase the feature diversity. The normalized feature-subsets can achieve better detection performance and also can be used as a useful complement for the existing steganalysis features. Experimental results show that: (1) a small amount of normalized feature-subset supplement can obviously improve the detection performance of SRM feature; (2) under the same dimensionality, the proposed NRS version feature can achieve a better detection accuracy than that of original feature; (3) the proposed NRS method is applicable to projections of spatial rich model feature; (4) compared with steganalysis feature extraction, the computational time of NRS can be negligible. [ABSTRACT FROM AUTHOR]

Current mainstream networks for hyperspectral image (HSI) classification employ image patches as inputs for feature extraction. Spatial information extraction is limited by the size of inputs, which makes networks unable to perform effective learning and reasoning from the global perspective. As a common component for capturing long-range dependencies, non-local networks with pixel-by-pixel information interaction bring unaffordable computational costs and information redundancy. To address the above issues, we propose a class feature fused fully convolutional network (CFF-FCN) with a local feature extraction block (LFEB) and a class feature fusion block (CFFB) to jointly utilize local and global information. LFEB based on dilated convolutions and reverse loop mechanism can acquire the local spectral–spatial features at multiple levels and deliver shallower layer features for coarse classification. CFFB calculates global class representation to enhance pixel features. Robust global information is propagated to every pixel with low computational cost. CFF-FCN considers a fully global class context and obtains more discriminative representation by concatenating high-level local features and re-integrated global features. Experimental results conducted on three real HSI data sets demonstrate that the proposed fully convolutional network is superior to multiple state-of-the-art deep learning-based approaches, especially in the case of a small number of training samples. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification accuracy has been greatly improved by employing deep learning. The current research mainly focuses on how to build a deep network to improve the accuracy. However, these networks tend to be more complex and have more parameters, which makes the model difficult to train and easy to overfit. Therefore, we present a lightweight deep convolutional neural network (CNN) model called S2FEF-CNN. In this model, three S2FEF blocks are used for the joint spectral–spatial features extraction. Each S2FEF block uses 1D spectral convolution to extract spectral features and 2D spatial convolution to extract spatial features, respectively, and then fuses spectral and spatial features by multiplication. Instead of using the full connected layer, two pooling layers follow three blocks for dimension reduction, which further reduces the training parameters. We compared our method with some state-of-the-art HSI classification methods based on deep network on three commonly used hyperspectral datasets. The results show that our network can achieve a comparable classification accuracy with significantly reduced parameters compared to the above deep networks, which reflects its potential advantages in HSI classification. [ABSTRACT FROM AUTHOR]

Fine-grained visual classification (FGVC) has small inter-class variations and large intra-class variations, therefore, recognizing sub-classes belonging to the same meta-class is a difficult task. Recent studies have primarily addressed this problem by locating the most discriminative image regions, and the extracted image regions have been used to improve the ability to capture subtle differences. Most of these studies used regular anchors to extract local features. However, the local features of the target are mostly irregular geometric shapes. These methods cannot fully extract the features and inevitably include a large amount of irrelevant information, resulting in reduced credibility of the evaluation results. However, the spatial relationship between the features is easily overlooked. This study proposes a novel local feature extraction anchor generator (LFEAG) to simulate the shapes of irregular features. Thus, discriminative features can be fully included in the extracted features. In addition, an effective symmetrized local feature extraction module (SLFEM) based on an attention mechanism is proposed to fully use the spatial relationship between the extracted local features and highlight discriminative features. Experiments on six popular fine-grained benchmark datasets: CUB-200-2011, Stanford Dogs, Food-101, Oxford-IIIT Pets, Aircraft and NA-Birds, are conducted to demonstrate the advantages of our proposed method. [ABSTRACT FROM AUTHOR]