DCNet: Densely Connected Deep Convolutional Encoder–Decoder Network for Nasopharyngeal Carcinoma Segmentation

Nasopharyngeal Carcinoma segmentation in magnetic resonance imagery (MRI) is vital to radiotherapy. Exact dose delivery hinges on an accurate delineation of the gross tumor volume (GTV). However, the large-scale variation in tumor volume is intractable, and the performance of current models is mostly unsatisfactory with indistinguishable and blurred boundaries of segmentation results of tiny tumor volume. To address the problem, we propose a densely connected deep convolutional network consisting of an encoder network and a corresponding decoder network, which extracts high-level semantic features from different levels and uses low-level spatial features concurrently to obtain fine-grained segmented masks. Skip-connection architecture is involved and modified to propagate spatial information to the decoder network. Preliminary experiments are conducted on 30 patients. Experimental results show our model outperforms all baseline models, with improvements of 4.17%. An ablation study is performed, and the effectiveness of the novel loss function is validated.

Download Full-text

Two-Level Attentions and Grouping Attention Convolutional Network for Fine-Grained Image Classification

Applied Sciences ◽

10.3390/app9091939 ◽

2019 ◽

Vol 9 (9) ◽

pp. 1939 ◽

Cited By ~ 5

Author(s):

Yadong Yang ◽

Xiaofeng Wang ◽

Quan Zhao ◽

Tingting Sui

Keyword(s):

Image Classification ◽

Feature Fusion ◽

Recognition Rate ◽

Fine Tuning ◽

Semantic Features ◽

Convolutional Network ◽

Attention Model ◽

Fine Grained ◽

Visual Attention Mechanism ◽

High Level

The focus of fine-grained image classification tasks is to ignore interference information and grasp local features. This challenge is what the visual attention mechanism excels at. Firstly, we have constructed a two-level attention convolutional network, which characterizes the object-level attention and the pixel-level attention. Then, we combine the two kinds of attention through a second-order response transform algorithm. Furthermore, we propose a clustering-based grouping attention model, which implies the part-level attention. The grouping attention method is to stretch all the semantic features, in a deeper convolution layer of the network, into vectors. These vectors are clustered by a vector dot product, and each category represents a special semantic. The grouping attention algorithm implements the functions of group convolution and feature clustering, which can greatly reduce the network parameters and improve the recognition rate and interpretability of the network. Finally, the low-level visual features and high-level semantic information are merged by a multi-level feature fusion method to accurately classify fine-grained images. We have achieved good results without using pre-training networks and fine-tuning techniques.

Download Full-text

Distractor-Aware Tracking with Multi-Task and Dynamic Feature Learning

Journal of Circuits System and Computers ◽

10.1142/s0218126621500316 ◽

2020 ◽

pp. 2150031

Author(s):

Weichun Liu ◽

Xiaoan Tang ◽

Chenglin Zhao

Keyword(s):

Correlation Filter ◽

Coarse Grained ◽

Dynamic Feature ◽

Semantic Features ◽

Low Level ◽

Fine Grained ◽

Semantic Embedding ◽

Training Stage ◽

Online Tracking ◽

High Level

Recently, deep trackers based on the siamese networking are enjoying increasing popularity in the tracking community. Generally, those trackers learn a high-level semantic embedding space for feature representation but lose low-level fine-grained details. Meanwhile, the learned high-level semantic features are not updated during online tracking, which results in tracking drift in presence of target appearance variation and similar distractors. In this paper, we present a novel end-to-end trainable Convolutional Neural Network (CNN) based on the siamese network for distractor-aware tracking. It enhances target appearance representation in both the offline training stage and online tracking stage. In the offline training stage, this network learns both the low-level fine-grained details and high-level coarse-grained semantics simultaneously in a multi-task learning framework. The low-level features with better resolution are complementary to semantic features and able to distinguish the foreground target from background distractors. In the online stage, the learned low-level features are fed into a correlation filter layer and updated in an interpolated manner to encode target appearance variation adaptively. The learned high-level features are fed into a cross-correlation layer without online update. Therefore, the proposed tracker benefits from both the adaptability of the fine-grained correlation filter and the generalization capability of the semantic embedding. Extensive experiments are conducted on the public OTB100 and UAV123 benchmark datasets. Our tracker achieves state-of-the-art performance while running with a real-time frame-rate.

Download Full-text

Hybrid Attention Network for Language-Based Person Search

Sensors ◽

10.3390/s20185279 ◽

2020 ◽

Vol 20 (18) ◽

pp. 5279

Author(s):

Yang Li ◽

Huahu Xu ◽

Junsheng Xiao

Keyword(s):

Image Features ◽

Attention Mechanism ◽

Feature Representation ◽

Semantic Features ◽

Retrieval Task ◽

Attention Network ◽

Fine Grained ◽

Person Search ◽

High Level ◽

Language Description

Language-based person search retrieves images of a target person using natural language description and is a challenging fine-grained cross-modal retrieval task. A novel hybrid attention network is proposed for the task. The network includes the following three aspects: First, a cubic attention mechanism for person image, which combines cross-layer spatial attention and channel attention. It can fully excavate both important midlevel details and key high-level semantics to obtain better discriminative fine-grained feature representation of a person image. Second, a text attention network for language description, which is based on bidirectional LSTM (BiLSTM) and self-attention mechanism. It can better learn the bidirectional semantic dependency and capture the key words of sentences, so as to extract the context information and key semantic features of the language description more effectively and accurately. Third, a cross-modal attention mechanism and a joint loss function for cross-modal learning, which can pay more attention to the relevant parts between text and image features. It can better exploit both the cross-modal and intra-modal correlation and can better solve the problem of cross-modal heterogeneity. Extensive experiments have been conducted on the CUHK-PEDES dataset. Our approach obtains higher performance than state-of-the-art approaches, demonstrating the advantage of the approach we propose.

Download Full-text

Technologies of Nanomodification of Low-Carbon Low Alloyed Steels

Materials Science Forum ◽

10.4028/www.scientific.net/msf.638-642.3123 ◽

2010 ◽

Vol 638-642 ◽

pp. 3123-3127

Author(s):

V.A. Malyshevsky ◽

E.I. Khlusova ◽

V.V. Orlov

Keyword(s):

Large Scale ◽

Physical And Mechanical Properties ◽

Metallurgical Industry ◽

Low Alloy Steels ◽

Scale Production ◽

Low Carbon ◽

Fine Grained ◽

Interphase Boundaries ◽

Alloy Steels ◽

High Level

Metallurgical industry can be considered as a field most accommodated for perception of nano-technologies, which in the near future will be able to provide large scale production and high level of investments return. Specially noted should physical and mechanical properties of nano-structured steels and alloys (strength, plasticity, toughness and so on) which will cardinally excel characteristics of respective materials developed using conventional technologies. Investigations have shown that basic principles of selection of a structure up to nano-level for low-carbon low-alloy steels can be put forward, that is: 1) morphological similarity of structural components, pre-domination of globular type structures due to reduction in carbon components and rational alloying; 2) formation of fine-dispersed carbide phase of globular morphology; 3) exclusion of lengthy interphase boundaries; 4) formation of fragmented structure with boundaries close to wide-angle ones, which inherited structure of fine-grained deformed austenite.

Download Full-text

Exploring Weighted Dual Graph Regularized Non-Negative Matrix Tri-Factorization Based Collaborative Filtering Framework for Multi-Label Annotation of Remote Sensing Images

Remote Sensing ◽

10.3390/rs11080922 ◽

2019 ◽

Vol 11 (8) ◽

pp. 922 ◽

Cited By ~ 3

Author(s):

Juli Zhang ◽

Junyi Zhang ◽

Tao Dai ◽

Zhanzhuang He

Keyword(s):

Remote Sensing ◽

Large Scale ◽

Dual Graph ◽

Semantic Features ◽

Label Graph ◽

Remote Sensing Images ◽

Graph Regularization ◽

Semantic Concepts ◽

High Level ◽

Laborious Work

Manually annotating remote sensing images is laborious work, especially on large-scale datasets. To improve the efficiency of this work, we propose an automatic annotation method for remote sensing images. The proposed method formulates the multi-label annotation task as a recommended problem, based on non-negative matrix tri-factorization (NMTF). The labels of remote sensing images can be recommended directly by recovering the image–label matrix. To learn more efficient latent feature matrices, two graph regularization terms are added to NMTF that explore the affiliated relationships on the image graph and label graph simultaneously. In order to reduce the gap between semantic concepts and visual content, both low-level visual features and high-level semantic features are exploited to construct the image graph. Meanwhile, label co-occurrence information is used to build the label graph, which discovers the semantic meaning to enhance the label prediction for unlabeled images. By employing the information from images and labels, the proposed method can efficiently deal with the sparsity and cold-start problem brought by limited image–label pairs. Experimental results on the UCMerced and Corel5k datasets show that our model outperforms most baseline algorithms for multi-label annotation of remote sensing images and performs efficiently on large-scale unlabeled datasets.

Download Full-text

Multilevel feature fusion dilated convolutional network for semantic segmentation

International Journal of Advanced Robotic Systems ◽

10.1177/17298814211007665 ◽

2021 ◽

Vol 18 (2) ◽

pp. 172988142110076

Author(s):

Tao Ku ◽

Qirui Yang ◽

Hao Zhang

Keyword(s):

Large Scale ◽

Semantic Information ◽

Spatial Information ◽

Feature Fusion ◽

Scene Perception ◽

Semantic Segmentation ◽

Field Size ◽

Data Set ◽

Dilated Convolution ◽

High Level

Recently, convolutional neural network (CNN) has led to significant improvement in the field of computer vision, especially the improvement of the accuracy and speed of semantic segmentation tasks, which greatly improved robot scene perception. In this article, we propose a multilevel feature fusion dilated convolution network (Refine-DeepLab). By improving the space pyramid pooling structure, we propose a multiscale hybrid dilated convolution module, which captures the rich context information and effectively alleviates the contradiction between the receptive field size and the dilated convolution operation. At the same time, the high-level semantic information and low-level semantic information obtained through multi-level and multi-scale feature extraction can effectively improve the capture of global information and improve the performance of large-scale target segmentation. The encoder–decoder gradually recovers spatial information while capturing high-level semantic information, resulting in sharper object boundaries. Extensive experiments verify the effectiveness of our proposed Refine-DeepLab model, evaluate our approaches thoroughly on the PASCAL VOC 2012 data set without MS COCO data set pretraining, and achieve a state-of-art result of 81.73% mean interaction-over-union in the validate set.

Download Full-text

Release the Power of Online-Training for Robust Visual Tracking

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i07.6956 ◽

2020 ◽

Vol 34 (07) ◽

pp. 12645-12652

Author(s):

Yifan Yang ◽

Guorong Li ◽

Yuankai Qi ◽

QIngming Huang

Keyword(s):

Visual Tracking ◽

High Performance ◽

Large Scale ◽

Feature Space ◽

Online Training ◽

Training Data ◽

Semantic Features ◽

Tracking Accuracy ◽

Tightly Coupled ◽

High Level

Convolutional neural networks (CNNs) have been widely adopted in the visual tracking community, significantly improving the state-of-the-art. However, most of them ignore the important cues lying in the distribution of training data and high-level features that are tightly coupled with the target/background classification. In this paper, we propose to improve the tracking accuracy via online training. On the one hand, we squeeze redundant training data by analyzing the dataset distribution in low-level feature space. On the other hand, we design statistic-based losses to increase the inter-class distance while decreasing the intra-class variance of high-level semantic features. We demonstrate the effectiveness on top of two high-performance tracking methods: MDNet and DAT. Experimental results on the challenging large-scale OTB2015 and UAVDT demonstrate the outstanding performance of our tracking method.

Download Full-text

Point Cloud Semantic Segmentation with Cross-Correction Features

10.21203/rs.3.rs-1218117/v1 ◽

2022 ◽

Author(s):

Yuehua Zhao ◽

Ma Jie ◽

Chong Nannan ◽

Wen Junjie

Keyword(s):

Real Time ◽

Point Cloud ◽

Large Scale ◽

Spatial Information ◽

Semantic Segmentation ◽

Autonomous Driving ◽

Basic Unit ◽

Semantic Features ◽

Point Cloud Segmentation ◽

Scale Point

Abstract Real time large scale point cloud segmentation is an important but challenging task for practical application like autonomous driving. Existing real time methods have achieved acceptance performance by aggregating local information. However, most of them only exploit local spatial information or local semantic information dependently, few considering the complementarity of both. In this paper, we propose a model named Spatial-Semantic Incorporation Network (SSI-Net) for real time large scale point cloud segmentation. A Spatial-Semantic Cross-correction (SSC) module is introduced in SSI-Net as a basic unit. High quality contextual features can be learned through SSC by correct and update semantic features using spatial cues, and vice verse. Adopting the plug-and-play SSC module, we design SSI-Net as an encoder-decoder architecture. To ensure efficiency, it also adopts a random sample based hierarchical network structure. Extensive experiments on several prevalent datasets demonstrate that our method can achieve state-of-the-art performance.

Download Full-text

Panchromatic Image Super-Resolution Via Self Attention-Augmented Wasserstein Generative Adversarial Network

Sensors ◽

10.3390/s21062158 ◽

2021 ◽

Vol 21 (6) ◽

pp. 2158

Author(s):

Juan Du ◽

Kuanhong Cheng ◽

Yue Yu ◽

Dabao Wang ◽

Huixin Zhou

Keyword(s):

Large Scale ◽

Spatial Information ◽

Super Resolution ◽

Attention Mechanism ◽

Feature Representation ◽

Similarity Function ◽

Feature Maps ◽

Generative Adversarial Network ◽

Convolutional Network ◽

Adversarial Network

Panchromatic (PAN) images contain abundant spatial information that is useful for earth observation, but always suffer from low-resolution ( LR) due to the sensor limitation and large-scale view field. The current super-resolution (SR) methods based on traditional attention mechanism have shown remarkable advantages but remain imperfect to reconstruct the edge details of SR images. To address this problem, an improved SR model which involves the self-attention augmented Wasserstein generative adversarial network ( SAA-WGAN) is designed to dig out the reference information among multiple features for detail enhancement. We use an encoder-decoder network followed by a fully convolutional network (FCN) as the backbone to extract multi-scale features and reconstruct the High-resolution (HR) results. To exploit the relevance between multi-layer feature maps, we first integrate a convolutional block attention module (CBAM) into each skip-connection of the encoder-decoder subnet, generating weighted maps to enhance both channel-wise and spatial-wise feature representation automatically. Besides, considering that the HR results and LR inputs are highly similar in structure, yet cannot be fully reflected in traditional attention mechanism, we, therefore, designed a self augmented attention (SAA) module, where the attention weights are produced dynamically via a similarity function between hidden features; this design allows the network to flexibly adjust the fraction relevance among multi-layer features and keep the long-range inter information, which is helpful to preserve details. In addition, the pixel-wise loss is combined with perceptual and gradient loss to achieve comprehensive supervision. Experiments on benchmark datasets demonstrate that the proposed method outperforms other SR methods in terms of both objective evaluation and visual effect.

Download Full-text

An Improved Method for Road Extraction from High-Resolution Remote-Sensing Images that Enhances Boundary Information

Sensors ◽

10.3390/s20072064 ◽

2020 ◽

Vol 20 (7) ◽

pp. 2064 ◽

Cited By ~ 4

Author(s):

Shuai Wang ◽

Hui Yang ◽

Qiangqiang Wu ◽

Zhiteng Zheng ◽

Yanlan Wu ◽

...

Keyword(s):

Remote Sensing ◽

Spatial Information ◽

Ground Truth ◽

Superior Performance ◽

Road Extraction ◽

Remote Sensing Images ◽

Feature Maps ◽

Convolutional Network ◽

The Road ◽

High Level

At present, deep-learning methods have been widely used in road extraction from remote-sensing images and have effectively improved the accuracy of road extraction. However, these methods are still affected by the loss of spatial features and the lack of global context information. To solve these problems, we propose a new network for road extraction, the coord-dense-global (CDG) model, built on three parts: a coordconv module by putting coordinate information into feature maps aimed at reducing the loss of spatial information and strengthening road boundaries, an improved dense convolutional network (DenseNet) that could make full use of multiple features through own dense blocks, and a global attention module designed to highlight high-level information and improve category classification by using pooling operation to introduce global information. When tested on a complex road dataset from Massachusetts, USA, CDG achieved clearly superior performance to contemporary networks such as DeepLabV3+, U-net, and D-LinkNet. For example, its mean IoU (intersection of the prediction and ground truth regions over their union) and mean F1 score (evaluation metric for the harmonic mean of the precision and recall metrics) were 61.90% and 76.10%, respectively, which were 1.19% and 0.95% higher than the results of D-LinkNet (the winner of a road-extraction contest). In addition, CDG was also superior to the other three models in solving the problem of tree occlusion. Finally, in universality research with the Gaofen-2 satellite dataset, the CDG model also performed well at extracting the road network in the test maps of Hefei and Tianjin, China.

Download Full-text