Search

Scene recognition is a computer vision task that categorizes scenes from photographs. In this paper, we introuduce the Adaptive Local Recalibration Network (ALR-Net), a novel scene recognition method based on convolutional neural networks (CNNs). In comparison to the object classification task, the scene classification images have a more dispersed distribution of information. To solve this issue, we suggest an attention mechanism for locating the discriminative regions for scene recognition. Along with normal data augmentation, we use the regions to guide two additional data augmentation approaches, namely adaptive cropping and adaptive hiding, in order to capture local information more efficiently and specifically. Attention maps are also used to adaptively recalibrate scene feature maps so that discriminative regions receive more attention than others. In addition, we bring in a scene distribution label for each image, which is used to assist the training of attention maps. Extensive studies on two scene recognition benchmarks verified the proposed model's effectiveness: MIT67 (88.37%) and SUN397 (74.24%). [ABSTRACT FROM AUTHOR]

Given the challenges encountered by industrial cameras, such as the randomness of sensor components, scattering, and polarization caused by optical defects, environmental factors, and other variables, the resulting noise hinders image recognition and leads to errors in subsequent image processing. In this study, we propose a RAW image denoising method based on BlockwiseUNet. By enabling local feature extraction and fusion, this approach enhances the network's capability to capture and suppress noise across multiple scales. We conducted extensive experiments on the SIDD benchmark (Smartphone Image Denoising Dataset), and the PSNR/SSIM value reached 51.25/0.992, which exceeds the current mainstream denoising methods. Additionally, our method demonstrates robustness to different noise levels and exhibits good generalization performance across various datasets. Furthermore, our proposed approach also exhibits certain advantages on the DND benchmark(Darmstadt Noise Dataset). [ABSTRACT FROM AUTHOR]

Airborne electromechanical actuators (EMAs) play a key role in the flight control system, and their health condition has a considerable impact on the flight status and safety of aircraft. Considering the multi-scale feature of fault signals and the fault diagnosis reliability for EMAs under complex working conditions, a novel fault diagnosis method of multi-scale feature fusion convolutional neural network (MSFFCNN) is proposed. Leveraging the multiple different scales' learning structure and attention mechanism-based feature fusion, the fault-related information can be effectively captured and learned, thereby improving the recognition ability and diagnostic performance of the network. The proposed method was evaluated by experiments and compared with the other three fault-diagnosis algorithms. The results show that the proposed MSFFCNN approach has a better diagnostic performance compared with the state-of-the-art fault diagnosis methods, which demonstrates the effectiveness and superiority of the proposed method. [ABSTRACT FROM AUTHOR]

Deep-learning-based segmentation methods have achieved excellent results. As two main tasks in computer vision, instance segmentation and semantic segmentation are closely related and mutually beneficial. Spatial context information from the semantic features can also improve the accuracy of instance segmentation. Inspired by this, we propose a novel instance segmentation framework named partial atrous cascade R-CNN (PAC), which effectively improves the accuracy of the segmentation boundary. The proposed network innovates in two aspects: (1) A semantic branch with a partial atrous spatial pyramid extraction (PASPE) module is proposed in this paper. The module consists of atrous convolution layers with multi-dilation rates. By expanding the receptive field of the convolutional layer, multi-scale semantic features are greatly enriched. Experiments shows that the new branch obtains more accurate segmentation contours. (2) The proposed mask quality (MQ) module scores the intersection over union (IoU) between the predicted mask and the ground truth mask. Benefiting from the modified mask quality score, the quality of the segmentation results is judged credibly. Our proposed network is trained and tested on the MS COCO dataset. Compared with the benchmark, it brings consistent and noticeable improvements in the case of using the same backbone. [ABSTRACT FROM AUTHOR]

Background: Prediction of protein solubility is an indispensable prerequisite for pharmaceutical research and production. The general and specific objective of this work is to design a new model for predicting protein solubility by using protein sequence feature fusion and deep dual-channel convolutional neural networks (DDcCNN) to improve the performance of existing prediction models. Methods: The redundancy of raw protein is reduced by CD-HIT. The four subsequences are built from protein sequence: one global and three locals. The global subsequence is the entire protein sequence, and these local subsequences are obtained by moving a sliding window with some rules. Using G-gap to extract the features of the above four subsequences, a mixed matrix is constructed as the input of one channel which is composed of three-layer convolutional operating. Additional features are extracted by SCRATCH tool as input of another channel, which is consist of a single convolution in order to find hidden relationships and improve the accuracy of predictor. The outputs of two parallel channels are concatenated as the input of the hidden layer. And the prediction of protein solubility is obtained in the output layer. The best protein solubility prediction model is obtained by doing some comparative experiments of different frameworks. Results: The performance indicators of DDcCNN model (our designed) are as follows: accuracy of 77.82%, Matthew's correlation coefficient of 0.57, sensitivity of 76.13% and specificity of 79.32%. The results of some comparative experiments show that the overall performance of DDcCNN model is better than existing models (GCNN, LCNN and PCNN). The related models and data are publicly deposited at http://www.ddccnn.wang. Conclusion: The satisfactory performance of DDcCNN model reveals that these features and flexible computational methodologies can reinforce the existing prediction models for better prediction of protein solubility could be applied in several applications, such as to preselect initial targets that are soluble or to alter solubility of target proteins, thus can help to reduce the production cost. [ABSTRACT FROM AUTHOR]

Current methods based on the traditional i-vectors and deep neural network (DNN) have shown effectiveness on the speaker identification task, especially with the corpus of large scale. However, when the size of the training dataset is small, the overfitting problem may happen and lead to performance degradation. Besides, the robust identification still remains a challenging problem even under the less strict requirements. This paper proposes a novel approach, SpeakerGAN, for speaker identification with the conditional generative adversarial network (CGAN). It allows the adversarial networks for distinguishing real/fake samples and predicting class labels simultaneously. We configure the generator and the discriminator in SpeakerGAN with the gated convolutional neural network (CNN) and the modified residual network (ResNet) to obtain generated samples of high diversity as well as increase the network capacity. The multiple loss functions are combined and optimized to encourage the correct mapping and accelerate the convergence. Experimental results show that SpeakerGAN reduces the classification error rate by 87% and 16% compared with the traditional i-vector system and the state-of-the-art DNN based method. Under the scenario of limited training data, SpeakerGAN obtains significant improvement over the baselines. In the case of taking 1.6 s of each speaker for testing, SpeakerGAN achieves the identification accuracy of 98.20%, which suggests the promise for short-utterance speaker identification. [ABSTRACT FROM AUTHOR]

Automatic aircraft engine defect detection is a challenging but important task in industry which can ensure safe air transportation and flight. In this paper, we propose a fast and accurate feature weighting network (FWNet) to solve the problem of defect scale variation and improve detection accuracy. The framework is designed based on recent popular convolutional neural networks and feature pyramid. To further boost the representation power of the network, a new feature weighting module (FWM) was proposed to recalibrate the channel-wise attention and increase the weights of valid features. The model was trained and tested on a self-built dataset, which consisted of 1916 images and contained three defect types: ablation, crack and coating missing. Extensive experimental results verify the effectiveness of the proposed FWM and show that the proposed method can accurately detect engine defects of different scales and different locations. Our method obtains 89.4% mAP and can run at 6FPS, which surpasses other state-of-the-art detection methods and can quickly provide diagnostic basis for aircraft maintenance inspectors in practical applications. [ABSTRACT FROM AUTHOR]

3D object detection in LiDAR point clouds has been extensively used in autonomous driving, intelligent robotics, and augmented reality. Although the one-stage 3D detector has satisfactory training and inference speed, there are still some performance problems due to insufficient utilization of bird's eye view (BEV) information. In this paper, a new backbone network is proposed to complete the cross-layer fusion of multi-scale BEV feature maps, which makes full use of various information for detection. Specifically, our proposed backbone network can be divided into a coarse branch and a fine branch. In the coarse branch, we use the pyramidal feature hierarchy (PFH) to generate multi-scale BEV feature maps, which retain the advantages of different levels and serves as the input of the fine branch. In the fine branch, our proposed pyramid splitting and aggregation (PSA) module deeply integrates different levels of multi-scale feature maps, thereby improving the expressive ability of the final features. Extensive experiments on the challenging KITTI-3D benchmark show that our method has better performance in both 3D and BEV object detection compared with some previous state-of-the-art methods. Experimental results with average precision (AP) prove the effectiveness of our network. [ABSTRACT FROM AUTHOR]

Spatiotemporal graph convolution has made significant progress in skeleton-based action recognition in recent years. Most of the existing graph convolution methods take all the joints of the human skeleton as the overall modeling graph, ignoring the differences in the movement patterns of various parts of the human, and cannot well connect the relationship between the different parts of the human skeleton. To capture the unique features of different parts of human skeleton data and the correlation of different parts, we propose two new graph convolution methods: the whole graph convolution network (WGCN) and the part graph convolution network (PGCN). WGCN learns the whole scale skeleton spatiotemporal features according to the movement patterns and physical structure of the human skeleton. PGCN divides the human skeleton graph into several subgraphs to learn the part scale spatiotemporal features. Moreover, we propose an adaptive fusion module that combines the two features for multiple complementary adaptive fusion to obtain more effective skeleton features. By coupling these proposals, we build a whole and part adaptive fusion graph convolution neural network (WPGCN) that outperforms previous state-of-the-art methods on three large-scale datasets: NTU RGB+D 60, NTU RGB+D 120, and Kinetics Skeleton 400. [ABSTRACT FROM AUTHOR]

In this work, we present a convolutional neural network (CNN) named CGFA-CNN for blind image quality assessment (BIQA). A unique two-stage strategy is utilized which firstly identifies the distortion type in an image using Sub-Network I and then quantifies this distortion using Sub-Network II. Different from most deep neural networks, we extract hierarchical features as descriptors to enhance the image representation and design a feature aggregation layer in an end-to-end training manner applying Fisher encoding to visual vocabularies modeled by Gaussian mixture models (GMMs). Considering the authentic distortions and synthetic distortions, the hierarchical feature contains the characteristics of a CNN trained on the self-built dataset and a CNN trained on ImageNet. We evaluated our algorithm on four publicly available databases, and the results demonstrate that our CGFA-CNN has superior performance over other methods both on synthetic and authentic databases. [ABSTRACT FROM AUTHOR]