首页/论文/2202.03430

arXiv 2202.034302022-02-07eess.IVcs.CV

A Topology-Attention ConvLSTM Network and Its Application to EM Images

Stony Brook University（石溪大学）；Graduate Center, CUNY（纽约市立大学研究生中心）

Jiaqi Yang, Xiaoling Hu, Chao Chen, Chialing Tsai

备注：: 12 pages, 6 figures, Accepted by MICCAI'21

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Structural accuracy of segmentation is important for finescale structures in biomedical images. We propose a novel TopologyAttention ConvLSTM Network (TACNet) for 3D image segmentation in order to achieve high structural accuracy for 3D segmentation tasks. Specifically, we propose a Spatial Topology-Attention (STA) module to process a 3D image as a stack of 2D image slices and adopt ConvLSTM to leverage contextual structure information from adjacent slices. In order to effectively transfer topology-critical information across slices, we propose an Iterative-Topology Attention (ITA) module that provides a more stable topology-critical map for segmentation. Quantitative and qualitative results show that our proposed method outperforms various baselines in terms of topology-aware evaluation metrics.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Temporally Identity-Aware SSD with Attentional LSTM

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Beijing Innovation Center for Engineering Science and Advanced Technology, Peking University（北京大学工程科学与先进技术北京创新中心）

Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithms have been developed for video detection task, yet very few approaches can achieve \emph{real-time online} object detection in videos. In this paper, based on attention mechanism and convolutional long short-term memory (ConvLSTM), we propose a temporal single-shot detector (TSSD) for real-world detection. Distinct from previous methods, we take aim at temporally integrating pyramidal feature hierarchy using ConvLST…

2020-03-25cs.CVcs.RO

A3CLNN: Spatial, Spectral and Multiscale Attention ConvLSTM Neural Network for Multisource Remote Sensing Data Classification

Southwest Jiaotong University（西南交通大学）

The problem of effectively exploiting the information multiple data sources has become a relevant but challenging research topic in remote sensing. In this paper, we propose a new approach to exploit the complementarity of two data sources: hyperspectral images (HSIs) and light detection and ranging (LiDAR) data. Specifically, we develop a new dual-channel spatial, spectral and multiscale attention convolutional long short-term memory neural network (called dual-channel A3CLNN) for feature extraction and classification of multisource remote sensing data. Spatial, spectral and multiscale attent…

2022-04-09cs.CVeess.IV

Dual Convolutional LSTM Network for Referring Image Segmentation

University of Manitoba（曼尼托巴大学）；Shanghai University（上海大学）

We consider referring image segmentation. It is a problem at the intersection of computer vision and natural language understanding. Given an input image and a referring expression in the form of a natural language sentence, the goal is to segment the object of interest in the image referred by the linguistic query. To this end, we propose a dual convolutional LSTM (ConvLSTM) network to tackle this problem. Our model consists of an encoder network and a decoder network, where ConvLSTM is used in both encoder and decoder networks to capture spatial and sequential information. The encoder networ…

2020-01-30cs.CV

RethNet: Object-by-Object Learning for Detecting Facial Skin Problems

lululab Inc（露露实验室公司）

Semantic segmentation is a hot topic in computer vision where the most challenging tasks of object detection and recognition have been handling by the success of semantic segmentation approaches. We propose a concept of object-by-object learning technique to detect 11 types of facial skin lesions using semantic segmentation methods. Detecting individual skin lesion in a dense group is a challenging task, because of ambiguities in the appearance of the visual data. We observe that there exist co-occurrent visual relations between object classes (e.g., wrinkle and age spot, or papule and whitehe…

2021-01-11cs.CV

基于图的WiFi信号3D人体姿态估计

Graph-based 3D Human Pose Estimation using WiFi Signals

本文提出GraphPose-Fi，一种基于图的WiFi信号3D人体姿态估计框架，通过建模骨骼拓扑结构提升估计精度。

2025-11-24cs.CV

Mosaic Super-resolution via Sequential Feature Pyramid Networks

CSIRO-Data61（澳大利亚联邦科学与工业研究组织-Data61）；Australian National University（澳大利亚国立大学）

Advances in the design of multi-spectral cameras have led to great interests in a wide range of applications, from astronomy to autonomous driving. However, such cameras inherently suffer from a trade-off between the spatial and spectral resolution. In this paper, we propose to address this limitation by introducing a novel method to carry out super-resolution on raw mosaic images, multi-spectral or RGB Bayer, captured by modern real-time single-shot mosaic sensors. To this end, we design a deep super-resolution architecture that benefits from a sequential feature pyramid along the depth of th…

2020-04-15cs.CVcs.LGeess.IV

更多相关论文收起更多论文

HTNet: Human Topology Aware Network for 3D Human Pose Estimation

Key Laboratory of Machine Perception, Shenzhen Graduate School, Peking University（北京大学深圳研究生院机器感知重点实验室）

3D human pose estimation errors would propagate along the human body topology and accumulate at the end joints of limbs. Inspired by the backtracking mechanism in automatic control systems, we design an Intra-Part Constraint module that utilizes the parent nodes as the reference to build topological constraints for end joints at the part level. Further considering the hierarchy of the human topology, joint-level and body-level dependencies are captured via graph convolutional networks and self-attentions, respectively. Based on these designs, we propose a novel Human Topology aware Network (HT…

2023-02-20cs.CVcs.HCcs.LG

TaGAT：用于多模态视网膜图像融合的拓扑感知图注意力网络

TaGAT: Topology-Aware Graph Attention Network For Multi-modal Retinal Image Fusion

University of Bristol（布里斯托尔大学）

提出TaGAT网络，通过拓扑感知编码器结合图注意力机制，融合多模态视网膜图像，保留血管拓扑细节，优于现有方法。

2024-07-19cs.CVeess.IV

PI-Att：通过自适应持久同调图像表示实现分割网络的拓扑注意力机制

PI-Att: Topology Attention for Segmentation Networks through Adaptive Persistence Image Representation

Koc University（科克大学）；Medical Sciences University（医科大学）；Haseki SUAM（哈塞基苏阿姆医院）

针对医学图像分割网络常忽略拓扑正确性的问题，提出一种基于自适应持久同调图像表示的拓扑感知损失PI-Att，可随训练进程自适应调整拓扑学习重点，在两个CT血管分割数据集上验证了有效性。

2024-08-15cs.CVeess.IV

HMS-VesselNet：具有拓扑保持损失的层次多尺度注意网络用于视网膜血管分割

HMS-VesselNet: Hierarchical Multi-Scale Attention Network with Topology-Preserving Loss for Retinal Vessel Segmentation

United Institute of Technology（印度科伊巴托尔大学）

本文提出HMS-VesselNet，通过多尺度网络和拓扑保持损失提升视网膜血管分割的精度，尤其改善了薄周缘血管的检测性能。

2026-03-23cs.CVeess.IV

Topo-VM-UNetV2：将拓扑编码融入视觉 Mamba UNet 以进行息肉分割

Topo-VM-UNetV2: Encoding Topology into Vision Mamba UNet for Polyp Segmentation

Department of Computer Science, University of Texas Rio Grande Valley（德克萨斯理工大学里奥格兰德分校计算机科学系）；Department of Mathematical Sciences, The University of Texas at Dallas（德克萨斯大学达拉斯分校数学科学系）

本文提出 Topo-VM-UNetV2，通过将拓扑注意力图融入 VM-UNetV2 的 SDI 模块，增强息肉分割中的边界描绘能力，并在五个公开数据集上验证了其有效性。

2025-05-09cs.CVeess.IV

MMV-Net: A Multiple Measurement Vector Network for Multi-frequency Electrical Impedance Tomography

Multi-frequency Electrical Impedance Tomography (mfEIT) is an emerging biomedical imaging modality to reveal frequency-dependent conductivity distributions in biomedical applications. Conventional model-based image reconstruction methods suffer from low spatial resolution, unconstrained frequency correlation and high computational cost. Deep learning has been extensively applied in solving the EIT inverse problem in biomedical and industrial process imaging. However, most existing learning-based approaches deal with the single-frequency setup, which is inefficient and ineffective when extended…

2021-05-26eess.IV