Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 17 papers published in subject: > since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Intensity-driven bounding box supervised brain white matter hyperintensities segmentation algorithm | |||
Cheng Ao | |||
Computer Science and Technology 08 March 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:White matter hyperintensities (WMHs) serves as a crucial imaging feature for assessing cerebral white matter abnormalities, and accurate segmentation of WMHs holds significant importance for tracking disease progression, evaluating treatment effects, and studying and understanding various neurological and geriatric disorders. Presently, deep learning-based methods for WMHs segmentation rely heavily on extensively annotated training data at the pixel level. However, the irregular shapes, random distribution, and fuzzy boundaries characteristic of WMHs make acquiring pixel-level precise labels prohibitively costly. To mitigate the reliance on pixel-level annotations, this paper introduces an intensity-driven bounding box supervised brain white matter hyperintensities segmentation algorithm (IDBB), which substitutes precise labels with weak bounding box labels during model training. IDBB employs an intensity-based adaptive thresholding method to generate pixel-level pseudo-labels from bounding box labels and trains the segmentation network using both Dice loss and cross-entropy loss. Additionally, this paper introduces a WMHs segmentation dataset containing bounding box labels of various sizes, serving as a benchmark dataset for bounding box supervised WMHs segmentation tasks. Results demonstrate that the proposed method achieves segmentation performance on the Dice similarity coefficient (DSC) comparable to 90\% of fully supervised methods, surpassing other weakly supervised approaches. Experimental validation illustrates the effectiveness of the proposed method in reducing annotation costs while achieving satisfactory segmentation performance. | |||
TO cite this article:Cheng Ao. Intensity-driven bounding box supervised brain white matter hyperintensities segmentation algorithm[OL].[ 8 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762582 |
2. An attention-enhanced neural network with distillation training for barcode detection | |||
Wang Zijian,Zhou Xiaoguang | |||
Computer Science and Technology 03 April 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Barcodes have played an essential role in our daily life. Localizing, or detecting them in real scenes in a fast and robust way has many practical applications. Recently, some deep learning-based methods have shown great potential in object detection. However, because barcodes are placed at any angle, vertical bounding boxes cannot sufficiently capture accurate orientation and scale information. In this paper, we propose a barcode detector that performs dense prediction to accurately locate the position of pixels belonging to the barcode region. For better detection performance, we design a spatial attention module to integrate global information adaptively, which can be easily plugged into the prediction backbone. Meanwhile, we employ the knowledge distillation training strategy to train a small student network with the help of a heavy teacher network. Extensive experiment results demonstrate that our method can perform real-time speed on CPU environments and locate barcodes in images with complex scenes. | |||
TO cite this article:Wang Zijian,Zhou Xiaoguang. An attention-enhanced neural network with distillation training for barcode detection[OL].[ 3 April 2023] http://en.paper.edu.cn/en_releasepaper/content/4759920 |
3. YoloDepth: Yolo with Monocular Depth Estimation for Object Distance Measurement | |||
Chen Fei-Yang,Jiao Ji-Chao | |||
Computer Science and Technology 13 February 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Environmental perception system is an important part of autonomous driving. A high-precision, real-time perception system can help the vehicles make feasible decisions and reasonable plans for the next step while driving. We propose a multi-task environmental perception network (YoloDepth) that can simultaneously perform traffic object detection and distance measurement. It consists of an encoder for feature extraction and two decoders for specific tasks. Our model performs excellently on COCO 2017 object detection dataset and KITTI monocular depth estimation dataset, achieving state-of-the-art speed and accuracy, and can process both visual perception tasks simultaneously on the embedded device Jeston AGX Xavier (18.3 FPS) in real-time and maintain great accuracy. | |||
TO cite this article:Chen Fei-Yang,Jiao Ji-Chao. YoloDepth: Yolo with Monocular Depth Estimation for Object Distance Measurement[OL].[13 February 2023] http://en.paper.edu.cn/en_releasepaper/content/4759099 |
4. Pseudo-label-based Decoupling Domain Adaptation for Long-tail Distribution with Domain Discrepancy | |||
Liu YiChen,Wu ZhenYu | |||
Computer Science and Technology 13 February 2023 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In real-world scenarios, machine learning tasks suffer from long-tail distribution or domain discrepancy problems, and many recent works have proposed effective methods to solve the challenges respectively. However, few studies have paid attention to the two problems simultaneously, since long-tail distribution and domain discrepancy both perhaps influence the generalization of machine learning models. Thus, according to the upper bound error theory, a design principle is given to solve the long-tail distribution with domain discrepancy problem (LT-DD) , and a pseudo-label-based decoupling domain adaptation method (PLD-DA) is proposed following the design principle in this paper.PLD-DA follows a two-stage domain adaptation framework, which trains a domain-invariant feature extractor on the original long-tail dataset at the first stage while adjusts the classifier with reweighting method at the second stage. To improve the classification confidence for the classifier, the pseudo-label information of target domain is introduced and a self-learning strategy is used. Experiments are conducted to show that our method could achieve a well-transfered feature extractor and a confident unbiased classifier simultaneously on LT-DD tasks, improves the model's generalization compared to end-end rebalancing domain adaptation methods. | |||
TO cite this article:Liu YiChen,Wu ZhenYu. Pseudo-label-based Decoupling Domain Adaptation for Long-tail Distribution with Domain Discrepancy[OL].[13 February 2023] http://en.paper.edu.cn/en_releasepaper/content/4759091 |
5. No-reference video quality assessment based on human attention system for background replacement applications | |||
WANG Yinan,WANG Jing,SHEN Qiwei | |||
Computer Science and Technology 25 February 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the wide application of image and video background replacement in many scenes such as short video production and high-definition video conference, more and more background replacement algorithms and video creations are produced. But there are great differences in the quality of image and video after replacement. Evaluating the quality of image and video after background replacement has important guiding significance in industry and academia. In the background replacement scene, the factors affecting the video quality after replacement include the distorsion of video frames, inter frame jitter, composition and chroma harmony. Among them, the accuracy and quality of video frames is a very important evaluation dimension. In this paper, we proposes a deep learning algorithm based on visual attention mechanism to realize the accuracy quality assessment in the application of video background replacement. Firstly, the convolution neural network (CNN) is designed to extract the distortion feature, and then the spatial saliency feature and temporal motion feature are fused through the attention mechanism. Finally, the subjective perception of video accuracy by human vision is fitted to evaluate the perception accuracy of background replacement videos. | |||
TO cite this article:WANG Yinan,WANG Jing,SHEN Qiwei. No-reference video quality assessment based on human attention system for background replacement applications[OL].[25 February 2022] http://en.paper.edu.cn/en_releasepaper/content/4756403 |
6. Adaptive and Attention-joint Supervision for Weakly Supervised Segmentation | |||
Ma Yue,Wan Hongjiang | |||
Computer Science and Technology 23 February 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Image-level weakly supervised semantic segmentation is a great challenge to compensate for the missing mask labels. Methods based on image-level labels primarily use class activation map (CAM) to approximate the segmentation mask. In view of the pseudo masks only focus on the class-specific discriminative regions of objects, various methods are explored to expand pseudo masks to cover ground-truths. Contemporary methods tend to use a lower threshold to distinguish objects and backgrounds in order to adjust CAMs for higher object coverage. However, too many backgrounds are misclassified into pseudo masks and excessive noise is trained in downstream tasks. To surmount this crux, we propose our Adaptive and Attention-joint Supervision method (AAJS). AAJS divides classification network into two branches and adds the trend of expansion and convergence to the two branches respectively for their class-specific features, i.e. regions activated by CAM. Each branch is adaptive constrained by another branch based on the confidence of the features. Then, the class-specific features are enriched so as to obtain a more accurate CAM at a lower threshold. Moreover, we propose an adaptive feature dropout method to prevent the classification network from relying too much on discriminative regions. AAJS are based on the experiments evaluated on PASCAL VOC 2012 and matches or exceeds the state-of-the-art performance compare to existing methods. | |||
TO cite this article:Ma Yue,Wan Hongjiang. Adaptive and Attention-joint Supervision for Weakly Supervised Segmentation[OL].[23 February 2022] http://en.paper.edu.cn/en_releasepaper/content/4756323 |
7. P-SANET: A HIGH-PRECISION REALTIME POINT CLOUD SEMANTIC SEGMENTATION FRAMEWORK | |||
GOU Xiaofeng,JIAO Jichao,ZHANG Chengkai | |||
Computer Science and Technology 10 January 2022 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Perception in autonomous system is an important task to guide decision execu-tion. Lidar point cloud is a type of dataset to complete perception task, it is rich in original information, easy to collect, and convenient to store. Compared to camera image, point cloud contains precise spatial information and adapts to various en-vironments, nevertheless, more information means more computing power con-sumption. The processing speed and accuracy are two key metrics of neural net-work framework. The traditional methods have to pay the price of reducing accu-racy for increasing processing speed. Though some frameworks preprocess point cloud into projected image, the 2D image tensor also contains a large number of redundant channel features in the traditional 2Dconvolution operation. In this pa-per, we propose a point clouds semantic segmentation framework, we replace the standard convolutional layer with a new sub-module, and it greatly reduces the amount of computation, besides, we introduce a sub-module to fuse the coordi-nate values and middle tensors. The framework in this paper is divided into three parts: spherical projection preprocessing module, En-Decoder module and data post-processing module. We use the SemanticKITTI dataset to conduct experi-ments, and the results show that our framework outperforms other frameworks both in prediction accuracy and prediction speed. We also use sparse point cloud dataset to test the generalization of our framework, and the experiments show that it performs better than other frameworks. Code is available at: https://github.com/windtries/P-SANet | |||
TO cite this article:GOU Xiaofeng,JIAO Jichao,ZHANG Chengkai. P-SANET: A HIGH-PRECISION REALTIME POINT CLOUD SEMANTIC SEGMENTATION FRAMEWORK[OL].[10 January 2022] http://en.paper.edu.cn/en_releasepaper/content/4755947 |
8. LCPN: Lightweight Single-Person Pose Estimation Based on Cascaded Pyramid Network | |||
Meng Ruoli,Fang Wei | |||
Computer Science and Technology 26 February 2021 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:he task of human pose estimation has been largely improved most recently. However, there are still a lot of challenges to apply it in practice, such as the limited network bandwidth, the privacy and security risks and so on. In this paper, we propose a lightweight human pose estimation model called LCPN, which takes depthwise separable convolution instead of standard convolution to lighten the network. Besides, we try to combine the heatmap prediction and coordinate regression in the keypoint prediction stage, which will further improve the efficiency of the network. The proposed approach achieves an excellent trade-off between speed and accuracy on the LSP and MPII datasets, and is very suitable to run on edge devices with lower computing power. | |||
TO cite this article:Meng Ruoli,Fang Wei. LCPN: Lightweight Single-Person Pose Estimation Based on Cascaded Pyramid Network[OL].[26 February 2021] http://en.paper.edu.cn/en_releasepaper/content/4753756 |
9. Residual Dilated Attention for Semantic Segmentation of Traffic Scene Understanding | |||
Haibo~Fan, Zulong~Diao, Dafang~Zhang | |||
Computer Science and Technology 21 May 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In recent years, the convolutional neural network has achieved remarkable success in semantic segmentation of traffic scene understanding. At present, the main problems in the field of semantic segmentation are as follows: 1) The repeated pooling and downsampling operations reduce resolution of traffic images in the convolutional networks, which leads to lose abundant spatial information and poor segmentation performance. 2) Traffic images contain many objects of different scales. How to accurately recognize and segment these multi-scale objects is another key problem in semantic segmentation. To handle these problems, this paper propose an image semantic segmentation method based on the Residual Dilated Attention. This method uses spatial CNN to extract high-level semantic information, and then uses the proposed model to capture low-level semantic information, and follows the designed sampling rules to set appropriate and effective sampling rates, and effectively aggregates multi-scale context information while maintaining high resolution of feature maps. Finally, this paper also designs a fusion module to effectively fuse the results generated by the spatial CNN and the Residual Dilated Attention. The method in this paper conducts a series of simulation experiments on CULane and CamVid traffic datasets, and achieves competitive results, proving the effectiveness of the proposed method. | |||
TO cite this article:Haibo~Fan, Zulong~Diao, Dafang~Zhang. Residual Dilated Attention for Semantic Segmentation of Traffic Scene Understanding[OL].[21 May 2020] http://en.paper.edu.cn/en_releasepaper/content/4752172 |
10. Anomaly Detection Based on Locality-preferred Recoding of GAN Network | |||
Wei Huang,WANG Jianzhu,DONG Bangyi,MENG Qinglong,SHI Chuan,LI Qingyong | |||
Computer Science and Technology 26 March 2020 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Deep neural networks, including deep auto-encoder (DAE) and generative adversarial networks (GAN), have been extensively applied for anomaly detection. These models generally assume that reconstruction errors should be lower for normal samples but higher for anomalies. However, it has been found that DAE based models can sometimes reconstruct anomalies very well and thus result in miss detection. To address this problem, we propose an anomaly detection model using GAN with locality-preferred recoding, named LRGAN. LRGAN is inspired by the observation that both normal and abnormal samples are not scattered throughout the latent space but clustered separately at some local regions. Therefore, a locality-preferred recoding (LR) module is designed to compulsively represent the latent vectors of anomalies by normal ones, making the reconstructions approach to normal samples and thereby enlarging the residuals. To partly avoid latent vectors of normal samples being recoded, we further put forward to detect anomalies using GAN with an adaptive LR ($ALR$), named LRGAN+. Our proposed method is evaluated on two public datasets (i.e., MNIST and CIFAR-10) and one Fasteners dataset from practical application, considering both one-class anomaly detection and multi-class anomaly detection scenarios. Experimental results demonstrate that LRGAN is comparable with state-of-the-art methods and LRGAN+ outperforms these methods on all datasets. | |||
TO cite this article:Wei Huang,WANG Jianzhu,DONG Bangyi, et al. Anomaly Detection Based on Locality-preferred Recoding of GAN Network[OL].[26 March 2020] http://en.paper.edu.cn/en_releasepaper/content/4751373 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated