Filters








8,134 Hits in 5.1 sec

Self-paced and self-consistent co-training for semi-supervised image segmentation [article]

Ping Wang, Jizong Peng, Marco Pedersoli, Yuanfeng Zhou, Caiming Zhang, Christian Desrosiers
2021 arXiv   pre-print
In this paper, we improve existing approaches for semi-supervised segmentation with a self-paced and self-consistent co-training method.  ...  Results show clear advantages in terms of performance compared to the standard co-training baselines and recently proposed state-of-the-art approaches for semi-supervised segmentation  ...  Acknowledgments This work was supported in part by the Natural Sciences and Engineering Research Council of Canada (NSERC) Discovery Grants Program under grant RGPIN-2018-05715.  ... 
arXiv:2011.00325v4 fatcat:xzprv3daabhlfeuzr4o2zraakq

Self-Paced Contrastive Learning for Semi-supervised Medical Image Segmentation with Meta-labels [article]

Jizong Peng, Ping Wang, Chrisitian Desrosiers, Marco Pedersoli
2021 arXiv   pre-print
We use the meta-labels for pre-training the image encoder as well as to regularize a semi-supervised training, in which a reduced set of annotated data is used for training.  ...  Results on three different medical image segmentation datasets show that our approach: i) highly boosts the performance of a model trained on a few scans, ii) outperforms previous contrastive and semi-supervised  ...  Pre-trained and semi-supervised Our next subsection reports results for the combination of Self-Paced Contrastive learning used for both pre-training and semi-supervised training (SP-Con (both)).  ... 
arXiv:2107.13741v2 fatcat:z3pozdnpozg73j7vj6hb6pc5la

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.  ...  [174] applied the idea of co-training to semi-supervised segmentation of medical images.  ... 
doi:10.1109/access.2021.3062380 fatcat:r5vsec2yfzcy5nk7wusiftyayu

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.  ...  , and 2) specialized methods that make use of unlabeled data, e.g., self-training [44] - [47] , consistency regularization [48] , co-training, self-supervised learning, and adversarial learning.  ... 
arXiv:2103.00429v1 fatcat:p44a5e34sre4nasea5kjvva55e

Self-supervised Transfer Learning for Instance Segmentation through Physical Interaction [article]

Andreas Eitel and Nico Hauff and Wolfram Burgard
2020 arXiv   pre-print
in a self-supervised manner.  ...  Instance segmentation of unknown objects from images is regarded as relevant for several robot skills including grasping, tracking and object sorting.  ...  ACKNOWLEDGMENTS We also thank the anonymous reviewers for suggestions.  ... 
arXiv:2005.09484v1 fatcat:navvvb7im5h5xklbs6kynpbrga

Few-Cost Salient Object Detection with Adversarial-Paced Learning [article]

Dingwen Zhang, Haibin Tian, Jungong Han
2021 arXiv   pre-print
Detecting and segmenting salient objects from given image scenes has received great attention in recent years.  ...  1k human-annotated training images.  ...  The self-paced regularizer proposed by Zhang et al. [36] consists of a 1 -norm, a 0.5,1 -norm, and a Laplacian term for considering the group property in co-saliency detection. Li et al.  ... 
arXiv:2104.01928v1 fatcat:vrcarkcjtrbgxfiii4znjdqz34

Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation

Qi Yao, Xiaojin Gong
2020 IEEE Access  
INDEX TERMS Weakly and semi-supervised semantic segmentation, self-attention, saliency. XIAOJIN GONG (Member, IEEE) received the B.A. and M.A.  ...  Moreover, by simply replacing the additional supervisions with partially labeled ground-truth, SGAN works effectively for semi-supervised semantic segmentation as well.  ...  SGAN UNDER SEMI-SUPERVISION In the semi-supervised setting, a small number of training images are provided with strong pixel-level labels and the rest have image-level tags only.  ... 
doi:10.1109/access.2020.2966647 fatcat:gp2dhzvl75curawframh3tzliy

EVALUATION OF SEMI-SUPERVISED LEARNING FOR CNN-BASED CHANGE DETECTION

E. Bousias Alexakis, C. Armenakis
2021 The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences  
The approach is based on the Mean Teacher method, a semi-supervised approach, successfully applied for image classification and for sematic segmentation of medical images.  ...  In this work we experiment with the implementation of a semi-supervised training approach in an attempt to improve the image semantic segmentation performance of models trained using a small number of  ...  ACKNOWLEDGEMENTS This work is financially supported by the Natural Sciences and Engineering Research Council of Canada (NSERC Discovery and CREATE grants) and York University.  ... 
doi:10.5194/isprs-archives-xliii-b3-2021-829-2021 fatcat:de3tnxo6sndlzayzc2zi5kctme

A Self-Paced Multiple-Instance Learning Framework for Co-Saliency Detection

Dingwen Zhang, Deyu Meng, Chao Li, Lu Jiang, Qian Zhao, Junwei Han
2015 2015 IEEE International Conference on Computer Vision (ICCV)  
To alleviate this problem, we propose a novel framework for this task, by naturally reformulating it as a multiple-instance learning (MIL) problem and further integrating it into a self-paced learning  ...  As an interesting and emerging topic, co-saliency detection aims at simultaneously extracting common salient objects in a group of images.  ...  Acknowledgements: This work was partially supported by the National Science Foundation of China under Grant 61473231, 61522207, 61373114, and 11131006.  ... 
doi:10.1109/iccv.2015.75 dblp:conf/iccv/ZhangMLJZH15 fatcat:hbib4dfu4rf77kxbwcyugez5q4

Robust Semi-Supervised Traffic Sign Recognition via Self-Training and Weakly-Supervised Learning

Obed Tettey Nartey, Guowu Yang, Sarpong Kwadwo Asare, Jinzhao Wu, Lady Nadia Frempong
2020 Sensors  
The framework integrates weakly-supervised learning and self-training with self-paced learning to generate attention maps to augment the training set and utilizes a novel pseudo-label generation and selection  ...  In this work, we propose a novel semi-supervised classification technique that is robust to small and unbalanced data.  ...  It integrates Weakly-Supervised Learning (WSL) [24] and Self-Paced Learning (SPL) [41] to build a semi-supervised learning model.  ... 
doi:10.3390/s20092684 pmid:32397197 pmcid:PMC7248915 fatcat:mnrq4g25ungxhjwju7dztagkx4

SPFTN: A Self-Paced Fine-Tuning Network for Segmenting Objects in Weakly Labelled Videos

Dingwen Zhang, Le Yang, Deyu Meng, Dong Xu, Junwei Han
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
To perform weakly supervised learning based on the deep neural network, we make the earliest effort to integrate the self-paced learning regime and the deep neural network into a unified and compatible  ...  framework, leading to the self-paced fine-tuning network.  ...  In future, we plan to further improve the learning regime and apply it in other weakly supervised learning tasks like weakly supervised image segmentation [23, 21, 14] and co-saliency detection [34]  ... 
doi:10.1109/cvpr.2017.567 dblp:conf/cvpr/ZhangYMXH17 fatcat:ixj26t5cmzgcbl27ushtb7nwni

Saliency Guided Self-attention Network for Weakly and Semi-supervised Semantic Segmentation [article]

Qi Yao, Xiaojin Gong
2020 arXiv   pre-print
Moreover, by simply replacing the additional supervisions with partially labeled ground-truth, SGAN works effectively for semi-supervised semantic segmentation as well.  ...  Weakly supervised semantic segmentation (WSSS) using only image-level labels can greatly reduce the annotation cost and therefore has attracted considerable research interest.  ...  SGAN Under Semi-supervision In the semi-supervised setting, a small number of training images are provided with strong pixel-level labels and the rest have image-level tags only.  ... 
arXiv:1910.05475v2 fatcat:27uvc7j7xvalzjji4ee6tvn3q4

Robust Medical Image Classification from Noisy Labeled Data with Global and Local Representation Guided Co-training [article]

Cheng Xue, Lequan Yu, Pengfei Chen, Qi Dou, Pheng-Ann Heng
2022 arXiv   pre-print
In this paper, we propose a novel collaborative training paradigm with global and local representation learning for robust medical image classification from noisy-labeled data to combat the lack of high  ...  Notably, we further design a novel global and local representation learning scheme to implicitly regularize the networks to utilize noisy samples in a self-supervised manner.  ...  We used self-paced MentorNet in this paper as we don't have the extra clean data. • ELR [28] : They leveraged semi-supervised learning techniques and regularization term to prevent memorization of false  ... 
arXiv:2205.04723v1 fatcat:zmumvcntnzdtfbauvt7nba2cyy

Annotation-efficient deep learning for automatic medical image segmentation [article]

Shanshan Wang, Cheng Li, Rongpin Wang, Zaiyi Liu, Meiyun Wang, Hongna Tan, Yaping Wu, Xinfeng Liu, Hui Sun, Rui Yang, Xin Liu, Jie Chen (+3 others)
2021 arXiv   pre-print
Three datasets containing 11,852 breast images from three medical centers are employed, and AIDE, utilizing 10% training annotations, consistently produces segmentation maps comparable to those generated  ...  Automatic medical image segmentation plays a critical role in scientific research and medical care.  ...  Acknowledgements This work was partly supported by Scientific and Technical Innovation 2030-"New Generation Author Contributions  ... 
arXiv:2012.04885v3 fatcat:hsmypf4ixzgyrbm4nvxf5e6rye

Unsupervised Outlier Detection via Transformation Invariant Autoencoder

Zhen Cheng, En Zhu, Siqi Wang, Pei Zhang, Wang Li
2021 IEEE Access  
adaptive self-paced learning in our TIAE framework.  ...  Next, to mitigate the negative effect of noise introduced by outliers and stabilize the network training, we select the most confident inliers likely examples in each epoch as the training set by incorporating  ...  INCORPORATING ADAPTIVE SELF-PACED LEARNING Unsupervised outlier detection is harder than semi-supervised learning because of the existence of outliers in training data.  ... 
doi:10.1109/access.2021.3065838 fatcat:jisbs3qdefhxlb2t2colv7bom4
« Previous Showing results 1 — 15 out of 8,134 results