Filters








361 Hits in 5.5 sec

A Two-Stream Mutual Attention Network for Semi-supervised Biomedical Segmentation with Noisy Labels [article]

Shaobo Min, Xuejin Chen, Zheng-Jun Zha, Feng Wu, Yongdong Zhang
2018 arXiv   pre-print
In this paper, we propose a Two-Stream Mutual Attention Network (TSMAN) that weakens the influence of back-propagated gradients caused by incorrect labels, thereby rendering the network robust to unclean  ...  Learning-based methods suffer from a deficiency of clean annotations, especially in biomedical segmentation.  ...  In this paper, we design a network that is less disturbed Data with Noisy Labels Two-Stream Mutual Attention Network Hierarchical Distillation Figure 1: The pipeline of our self-training framework.  ... 
arXiv:1807.11719v3 fatcat:2qvalspasrfevhtbbtue2v52ju

A Two-Stream Mutual Attention Network for Semi-Supervised Biomedical Segmentation with Noisy Labels

Shaobo Min, Xuejin Chen, Zheng-Jun Zha, Feng Wu, Yongdong Zhang
2019 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
In this paper, we propose a Two-Stream Mutual Attention Network (TSMAN) that weakens the influence of back-propagated gradients caused by incorrect labels, thereby rendering the network robust to unclean  ...  By exchanging multi-level features within two-stream architecture, the effects of noisy labels in each sub-network are reduced by decreasing the noisy gradients.  ...  In this paper, we design a network that is less disturbed by noisy labels and propose a Data with Noisy Labels Two-Stream Mutual Attention Network Hierarchical Distillation Figure 1: The pipeline of  ... 
doi:10.1609/aaai.v33i01.33014578 fatcat:2izgzjmyivdrlfgwuiuebbtw4y

Uncertainty-Guided Mutual Consistency Learning for Semi-Supervised Medical Image Segmentation [article]

Yichi Zhang, Qingcheng Liao, Rushi Jiao, Jicong Zhang
2021 arXiv   pre-print
Experimental results demonstrate that our method achieves performance gains by leveraging unlabeled data and outperforms existing semi-supervised segmentation methods.  ...  Semi-supervised learning has been widely applied to medical image segmentation tasks since it alleviates the heavy burden of acquiring expert-examined annotations and takes the advantage of unlabeled data  ...  Zhang, “A two-stream mutual attention network for semi-supervised biomedical segmentation V.  ... 
arXiv:2112.02508v1 fatcat:ofgv42dygvhyxphgh2wbcgdvoy

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models [article]

Jialin Peng, Ye Wang
2021 arXiv   pre-print
The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling.  ...  However, due to its intrinsic difficulty, segmentation with limited supervision is challenging and specific model design and/or learning strategies are needed.  ...  [303] introduced a two-stream mutual attention network with hierarchical distillation, where the multiple attention layers were used to discover incorrect labels and indicate potentially incorrect gradients  ... 
arXiv:2103.00429v1 fatcat:p44a5e34sre4nasea5kjvva55e

Medical Image Segmentation with Limited Supervision: A Review of Deep Network Models

Jialin Peng, Ye Wang
2021 IEEE Access  
INDEX TERMS Medical image segmentation, semi-supervised segmentation, partially-supervised segmentation, noisy label, sparse annotation. 36828  ...  The labeling costs for medical images are very high, especially in medical image segmentation, which typically requires intensive pixel/voxel-wise labeling.  ...  [303] introduced a two-stream mutual attention network with hierarchical distillation, where the multiple attention layers were used to discover incorrect labels and indicate potentially incorrect gradients  ... 
doi:10.1109/access.2021.3062380 fatcat:r5vsec2yfzcy5nk7wusiftyayu

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
Nie, Y., +, TIP 2020 1465-1478 Compositional Attention Networks With Two-Stream Fusion for Video Question Answering.  ...  Nazir, A., +, TIP 2020 7192-7202 One-Pass Multi-Task Networks With Cross-Task Guided Attention for Brain Tumor Segmentation.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

2020 Index IEEE/ACM Transactions on Audio, Speech, and Language Processing Vol. 28

2020 IEEE/ACM Transactions on Audio Speech and Language Processing  
Azad, A., +, TASLP 2020 592-604 Semi-Supervised Neural Chord Estimation Based on a Variational Auto- encoder With Latent Chord Labels and Features.  ...  ., +, TASLP 2020 813-824 Semi-Supervised Neural Chord Estimation Based on a Variational Autoencoder With Latent Chord Labels and Features.  ...  T Target tracking Multi-Hypothesis Square-Root Cubature Kalman Particle Filter for Speaker Tracking in Noisy and Reverberant Environments. Zhang, Q., +, TASLP 2020 1183 -1197  ... 
doi:10.1109/taslp.2021.3055391 fatcat:7vmstynfqvaprgz6qy3ekinkt4

Gesture Recognition in Robotic Surgery: a Review

Beatrice Vanamsterdam, Matthew Clarkson, Danail Stoyanov
2021 IEEE Transactions on Biomedical Engineering  
While new strategies for discriminative feature extraction and knowledge transfer, or unsupervised and semi-supervised approaches, can mitigate the need for data and labels, they have not yet been demonstrated  ...  , trajectory, segmentation, recognition, parsing.  ...  To mitigate data requirements, the recognition problem can be tackled in a semi-supervised or unsupervised manner, where labels are only necessary for model testing.  ... 
doi:10.1109/tbme.2021.3054828 pmid:33497324 fatcat:si5dcvrvnzc55dse6cst2k5tfi

Graph Neural Networks: Methods, Applications, and Opportunities [article]

Lilapati Waikhom, Ripon Patgiri
2021 arXiv   pre-print
This article provides a comprehensive survey of graph neural networks (GNNs) in each learning setting: supervised, unsupervised, semi-supervised, and self-supervised learning.  ...  Traditionally, handcrafted features for graphs are incapable of providing the necessary inference for various tasks from this complex data representation.  ...  Graph-Based Semi-Supervised Learning Semi-supervised learning has been around for many years.  ... 
arXiv:2108.10733v2 fatcat:j3rfmkiwenebvmfyboasjmx4nu

Deep Learning of Unified Region, Edge, and Contour Models for Automated Image Segmentation [article]

Ali Hatamizadeh
2020 arXiv   pre-print
that unifies CNNs and active contour models with learnable parameters for fast and robust object delineation, (3) a novel approach for disentangling edge and texture processing in segmentation networks  ...  , and (4) a novel few-shot learning model in both supervised settings and semi-supervised settings where synergies between latent and image spaces are leveraged to learn to segment images given limited  ...  A.3.1.2 Atlas-Based Segmentation Another variation of reliant segmentation is registration using mutual information with a previously segmented atlas.  ... 
arXiv:2006.12706v1 fatcat:6jchhrv6zrhlhbpcak6fcbh4a4

2021 Index IEEE Transactions on Image Processing Vol. 30

2021 IEEE Transactions on Image Processing  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  ., +, TIP 2021 572-587 A Supervised Segmentation Network for Hyperspectral Image Classification.  ...  ., +, TIP 2021 6335-6348 A Supervised Segmentation Network for Hyperspectral Image Classification.  ... 
doi:10.1109/tip.2022.3142569 fatcat:z26yhwuecbgrnb2czhwjlf73qu

Survey on Deep Multi-modal Data Analytics: Collaboration, Rivalry and Fusion [article]

Yang Wang
2020 arXiv   pre-print
With the development of web technology, multi-modal or multi-view data has surged as a major stream for big data, where each modal/view encodes individual property of data objects.  ...  Recently, deep neural networks have exhibited as a powerful architecture to well capture the nonlinear distribution of high-dimensional multimedia data, so naturally does for multi-modal data.  ...  Then, the network is learned in a self-supervised manner with the labels inherited from visible images.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey [article]

Gabriela Csurka, Riccardo Volpi, Boris Chidlovskii
2021 arXiv   pre-print
Semantic segmentation plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image.  ...  We present the most important semantic segmentation methods; we provide a comprehensive survey on domain adaptation techniques for semantic segmentation; we unveil newer trends such as multi-domain learning  ...  The two networks image-level label distribution to guide the pixel-level target share the same architecture with an embedded attention module. segmentation.  ... 
arXiv:2112.03241v1 fatcat:uzlehddvuvfwzf4dfbjimja45e

Learning Neural Textual Representations for Citation Recommendation

Binh Thanh Kieu, Inigo Jauregi Unanue, Son Bao Pham, Hieu Xuan Phan, Massimo Piccardi
2021 2020 25th International Conference on Pattern Recognition (ICPR)  
H.; Leung, Howard 858 A Two-Stream Recurrent Network for Skeleton-Based Human Interaction Recognition DAY 4 -Jan 15, 2021 Orozco-Alzate, Mauricio; Bicego, Manuele 861 A Cheaper Rectified-Nearest-Feature-Line-Segment  ...  with Scarce Labelled Data: Semi-Supervised Deep Learning with Mix Match for Covid-19 Detection Using Chest X-Ray Images DAY 2 -Jan 13, 2021 Nguyen, Phuc; lathuiliere, Stéphane; Ricci, Elisa 1470  ... 
doi:10.1109/icpr48806.2021.9412725 fatcat:3vge2tpd2zf7jcv5btcixnaikm

Revise-Net: Exploiting Reverse Attention Mechanism for Salient Object Detection

Rukhshanda Hussain, Yash Karbhari, Muhammad Fazal Ijaz, Marcin Woźniak, Pawan Kumar Singh, Ram Sarkar
2021 Remote Sensing  
Finally, multiple reverse attention modules at varying scales are cascaded between the two networks to guide the prediction module by employing the intermediate segmentation maps generated at each downsampling  ...  The proposed Revise-Net model is divided into three parts: (a) the prediction module, (b) a residual enhancement module, and (c) reverse attention modules.  ...  A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision.  ... 
doi:10.3390/rs13234941 fatcat:4jno22evrvehbm4zznwfi43yp4
« Previous Showing results 1 — 15 out of 361 results