Filters








3,250 Hits in 9.2 sec

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  ...  We evaluated our proposed robust learning strategy on four public medical image classification datasets with three types of label noise,ie,random noise, computer-generated label noise, and inter-observer  ...  CONCLUSION In this paper, we present a global and local representation guided co-training strategy to address the challenging yet important noisy label issue for medical image analysis.  ... 
arXiv:2205.04723v1 fatcat:zmumvcntnzdtfbauvt7nba2cyy

Robust Federated Learning with Noisy Labels [article]

Seunghan Yang, Hyoungseob Park, Junyoung Byun, Changick Kim
2020 arXiv   pre-print
Although a lot of studies have been conducted to train the networks robust to these noisy data in a centralized setting, these algorithms still suffer from noisy labels in federated learning.  ...  Furthermore, we propose a global-guided pseudo-labeling method to update labels of unconfident samples by exploiting the global model.  ...  The client utilizes the server parameters (F G and C G ) for global-guided pseudo-labeling and constrains local feature representations with the global centroids.  ... 
arXiv:2012.01700v1 fatcat:svtwafdzwzhozjy6ztpat67muq

Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directions [article]

Anil Rahate, Rahee Walambe, Sheela Ramanna, Ketan Kotecha
2021 arXiv   pre-print
However, in real-world tasks, typically, it is observed that one or more modalities are missing, noisy, lacking annotated data, have unreliable labels, and are scarce in training or testing and or both  ...  Multimodal machine learning involves multiple aspects: representation, translation, alignment, fusion, and co-learning.  ...  Noise generators with adversarial learning generate noise based on local image distribution and global and universal features across the modalities or dataset.  ... 
arXiv:2107.13782v2 fatcat:s4spofwxjndb7leqbcqnwbifq4

Deep Co-Attention Network for Multi-View Subspace Learning [article]

Lecheng Zheng, Yu Cheng, Hongxia Yang, Nan Cao, Jingrui He
2021 arXiv   pre-print
In particular, it uses a novel cross reconstruction loss and leverages the label information to guide the construction of the latent representation by incorporating the classifier into our model.  ...  adversarial setting and provide robust interpretations behind the prediction to the end-users via the co-attention mechanism.  ...  For all the experiments, we randomly sample 32,000 examples from the Noisy MNIST data set as our training data, and 10,000 examples as the test data.  ... 
arXiv:2102.07751v1 fatcat:ufmiwpf7szbpzkrw6go7fv72ru

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.  ...  application of deep learning models in medical image segmentation.  ...  Co-training Co-training initially introduced by Blum and Mitchell [172] exploits multiview data descriptions to learn from a limited number of labeled examples and a large amount of unlabeled data.  ... 
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.  ...  CO-TRAINING Co-training initially introduced by Blum and Mitchell [172] exploits multiview data descriptions to learn from a limited number of labeled examples and a large amount of unlabeled data.  ... 
doi:10.1109/access.2021.3062380 fatcat:r5vsec2yfzcy5nk7wusiftyayu

Weakly Supervised Object Localization and Detection: A Survey [article]

Dingwen Zhang, Junwei Han, Gong Cheng, Ming-Hsuan Yang
2021 arXiv   pre-print
In this work, we review (1) classic models, (2) approaches with feature representations from off-the-shelf deep networks, (3) approaches solely based on deep learning, and (4) publicly available datasets  ...  As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems  ...  These priors can be used to guide the weakly supervised learning process on medical imaging data.  ... 
arXiv:2104.07918v1 fatcat:dwl6sjfzibdilnvjnrbifp4uke

Visual Sentiment Prediction Based on Automatic Discovery of Affective Regions

Jufeng Yang, Dongyu She, Ming Sun, Ming-Ming Cheng, Paul L. Rosin, Liang Wang
2018 IEEE transactions on multimedia  
Finally, the CNN outputs from local regions are aggregated with the whole images to produce the final predictions.  ...  While most of the current methods focus on improving holistic representations, we aim to utilize the local information, which is inspired by the observation that both the whole image and local regions  ...  This is far from the required scale for training robust deep models. The Flickr dataset [17] is weakly-labeled with 2 categories using the meta-data provided by the up-loaders.  ... 
doi:10.1109/tmm.2018.2803520 fatcat:smg75tgwxffxbandnubqgp32sa

Deep Metric Learning for Few-Shot Image Classification: A Review of Recent Developments [article]

Xiaoxu Li, Xiaochen Yang, Zhanyu Ma, Jing-Hao Xue
2022 arXiv   pre-print
We conclude this review with a discussion on current challenges and future trends in few-shot image classification.  ...  In this paper, we provide an up-to-date review of deep metric learning methods for few-shot image classification from 2018 to 2022 and categorize them into three groups according to three stages of metric  ...  Moreover, training episodes are revised to include noisy data, and a new evaluation metric is proposed to evaluate the robustness of few-shot classification methods. Ma et al.  ... 
arXiv:2105.08149v2 fatcat:yxsvfdspbrhfpcrzgnny27vgjy

Recent advances and clinical applications of deep learning in medical image analysis [article]

Xuxin Chen, Ximin Wang, Ke Zhang, Roy Zhang, Kar-Ming Fung, Theresa C. Thai, Kathleen Moore, Robert S. Mannel, Hong Liu, Bin Zheng, Yuchen Qiu
2021 arXiv   pre-print
scenarios, including classification, segmentation, detection, and image registration.  ...  Deep learning has received extensive research interest in developing new medical image processing algorithms, and deep learning based models have been remarkably successful in a variety of medical imaging  ...  Pseudo labeling also works well with multi-view co-training (Qiao et al., 2018) .  ... 
arXiv:2105.13381v2 fatcat:2k342a6rhjaavpoa2qoqxhg5rq

Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation [article]

Nima Tajbakhsh, Laura Jeyaseelan, Qian Li, Jeffrey Chiang, Zhihao Wu, Xiaowei Ding
2020 arXiv   pre-print
data is available for training, and weak annotations where the training data has only sparse annotations, noisy annotations, or image-level annotations.  ...  However, rarely do we have a perfect training dataset, particularly in the field of medical imaging, where data and annotations are both expensive to acquire.  ...  medical data and then fine-tuning the model for the target segmentation task Learning with image-level annotations Class activation maps Training a classification model with global average pooling and  ... 
arXiv:1908.10454v2 fatcat:mjvfbhx75bdkbheysq3r7wmhdi

Robust Classification from Noisy Labels: Integrating Additional Knowledge for Chest Radiography Abnormality Assessment [article]

Sebastian Gündel, Arnaud A. A. Setio, Florin C. Ghesu, Sasa Grbic, Bogdan Georgescu, Andreas Maier, Dorin Comaniciu
2021 arXiv   pre-print
Prior label probabilities were measured on a subset of training data re-read by 4 board-certified radiologists and were used during training to increase the robustness of the training model to the label  ...  In this study, we propose novel training strategies that handle label noise from such suboptimal data.  ...  Acknowledgement The authors thank the National Cancer Institute (NCI) for access to their data collected by the Prostate, Lung, Colorectal and Ovarian (PLCO) Cancer Screening Trial.  ... 
arXiv:2104.05261v3 fatcat:qdspeqfhvbc7rgtwmbkzyv65vm

A REVIEW STUDY OF METHODS UTILIZED FOR IDENTIFYING AND SEGMENTING THE BRAIN TUMOR FROM MR IMAGERIES

MOHD SHAFRY MOHD RAHIM AHMED SAIFULLAH SAMI
2019 Zenodo  
This paper provides a detailed analysis of the existent methods and approaches utilized in medical image segmentation.  ...  The process will also remain instrumental in the identification of additional abnormalities that can be extracted from computerized images of human brain.  ...  For classification, four supervised robust classification techniques like the SVM, NSC, SRC, KNN and one unsupervised clustering method, k-means were used and the results were compared After training the  ... 
doi:10.5281/zenodo.3256441 fatcat:xiqd75juvbbhnjbwffgruujnbi

2020 Index IEEE Transactions on Image Processing Vol. 29

2020 IEEE Transactions on Image Processing  
., +, TIP 2020 9445-9457 Siamese Local and Global Networks for Robust Face Tracking. Qi, Y., +, Text Co-Detection in Multi-View Scene.  ...  ., +, TIP 2020 8163-8176 Semi-Supervised Image Dehazing. Li, L., +, TIP 2020 2766-2779 Siamese Local and Global Networks for Robust Face Tracking.  ... 
doi:10.1109/tip.2020.3046056 fatcat:24m6k2elprf2nfmucbjzhvzk3m

Vision Transformers in Medical Computer Vision – A Contemplative Retrospection [article]

Arshi Parvaiz, Muhammad Anwaar Khalid, Rukhsana Zafar, Huma Ameer, Muhammad Ali, Muhammad Moazam Fraz
2022 arXiv   pre-print
These computer vision algorithms are being practised in medical image analysis and are transfiguring the perception and interpretation of Imaging data.  ...  Along with this, we also demystify several imaging modalities used in Medical Computer Vision.  ...  They suppressed the last classification layer of the pre-trained model to extract global and regional features from medical images.  ... 
arXiv:2203.15269v1 fatcat:wecjpoikbvfz5cygytqpktoxdq
« Previous Showing results 1 — 15 out of 3,250 results