15,680 Hits in 3.4 sec

Multi-Modal Curriculum Learning for Semi-Supervised Image Classification

Chen Gong, Dacheng Tao, Stephen J. Maybank, Wei Liu, Guoliang Kang, Jie Yang
2016 IEEE Transactions on Image Processing  
Semi-supervised image classification aims to classify a large quantity of unlabeled images by harnessing typically scarce labeled images.  ...  Existing semi-supervised methods often suffer from inadequate classification accuracy when encountering difficult yet critical images such as outliers, because they treat all unlabeled images equally and  ...  Semi-supervised Image Classification Semi-supervised learning (SSL) [12] has been studied for a long history, which aims to classify a massive number of unlabeled examples given the existence of only  ... 
doi:10.1109/tip.2016.2563981 pmid:27168596 fatcat:fgothu5cpvgwfdx3ikzxfzjwje

Multimodal Semi-Supervised Learning for 3D Objects [article]

Zhimin Chen, Longlong Jing, Yang Liang, YingLi Tian, Bing Li
2021 arXiv   pre-print
In recent years, semi-supervised learning has been widely explored and shows excellent data efficiency for 2D data.  ...  We propose a novel multimodal semi-supervised learning framework by introducing instance-level consistency constraint and a novel multimodal contrastive prototype (M2CP) loss.  ...  Although many semi-supervised learning methods have been proposed for 2D-related image recognition tasks, semi-supervised learning for 3D-related tasks has not been widely explored.  ... 
arXiv:2110.11601v2 fatcat:wbfjtsrhtngvbeppcexifpo2hu

Heterogeneous Image Features Integration via Multi-modal Semi-supervised Learning Model

Xiao Cai, Feiping Nie, Weidong Cai, Heng Huang
2013 2013 IEEE International Conference on Computer Vision  
Therefore, how to integrate heterogeneous visual features to do the semi-supervised learning is crucial for categorizing large-scale image data.  ...  Considering each type of feature as one modality, taking advantage of the large amount of unlabeled data information, our new adaptive multimodal semi-supervised classification (AMMSS) algorithm learns  ...  The most popular way to do semi-supervised learning for image categorization is to use some low-level image descriptors.  ... 
doi:10.1109/iccv.2013.218 dblp:conf/iccv/CaiNCH13a fatcat:exig5ikgeral3mqvwbe4luybl4

Multi-modal Sentiment Classification with Independent and Interactive Knowledge via Semi-supervised Learning

Dong Zhang, Shoushan Li, Qiaoming Zhu, Guodong Zhou
2020 IEEE Access  
In this paper, we aim to reduce the annotation effort for multi-modal sentiment classification via semi-supervised learning.  ...  Empirical evaluation demonstrates the great effectiveness of the proposed semi-supervised approach to multi-modal sentiment classification.  ...  AUDIO AND VIDEO-BASED SEMI-SUPERVISED SENTIMENT CLASSIFICATION Early multi-modal semi-supervised sentiment classification is based on multiple sources of images [11] , [26] .  ... 
doi:10.1109/access.2020.2969205 fatcat:bkcydvpc7bgs3l6n4usfz7lvcy

Manifold Regularized Multi-Task Feature Selection for Multi-Modality Classification in Alzheimer's Disease [chapter]

Biao Jie, Daoqiang Zhang, Bo Cheng, Dinggang Shen
2013 Lecture Notes in Computer Science  
Recently, multi-modality methods have been used for fusing information from multiple different and complementary imaging and non-imaging modalities.  ...  Specifically, we formulate the multi-modality classification as a multi-task learning framework, where each task focuses on the classification based on each modality.  ...  Semi-supervised M2TFS (Semi-M2TFS) Generally, semi-supervised learning methods attempt to exploit the intrinsic data distribution disclosed by the unlabeled data and thus help to construct a better learning  ... 
doi:10.1007/978-3-642-40811-3_35 fatcat:435f3z7pdnd7fgfhjpu756dcie

A Survey of Cross-Modality Brain Image Synthesis [article]

Guoyang Xie, Jinbao Wang, Yawen Huang, Yefeng Zheng, Feng Zheng, Yaochu Jin
2022 arXiv   pre-print
A realistic solution is to explore either an unsupervised learning or a semi-supervised learning to synthesize the absent neuroimaging data.  ...  In this paper, we tend to approach multi-modality brain image synthesis task from different perspectives, which include the level of supervision, the range of modality synthesis, and the synthesis-based  ...  [Yu et al.] introduce semi- Synthesis from Applies For brain lesion With downstream With downstream supervised MRI image to unsupervised detection classification task segmentation task learning PET image  ... 
arXiv:2202.06997v2 fatcat:kqxte2xrcrcpjfkkhwrcxdjqsu

Trash to Treasure: Harvesting OOD Data with Cross-Modal Matching for Open-Set Semi-Supervised Learning [article]

Junkai Huang, Chaowei Fang, Weikai Chen, Zhenhua Chai, Xiaolin Wei, Pengxu Wei, Liang Lin, Guanbin Li
2021 arXiv   pre-print
While the mainstream technique seeks to completely filter out the OOD samples for semi-supervised learning (SSL), we propose a novel training mechanism that could effectively exploit the presence of OOD  ...  Open-set semi-supervised learning (open-set SSL) investigates a challenging but practical scenario where out-of-distribution (OOD) samples are contained in the unlabeled data.  ...  Related Works Semi-Supervised Learning.  ... 
arXiv:2108.05617v1 fatcat:e3hkqoboq5ewnodvphe5unkl3a

Human Activity Recognition Using Semi-supervised Multi-modal DEC for Instagram Data [chapter]

Dongmin Kim, Sumin Han, Heesuk Son, Dongman Lee
2020 Lecture Notes in Computer Science  
In this paper, we propose a semi-supervised multi-modal deep embedding clustering method to recognize human activities on Instagram.  ...  Our proposed method learns multi-modal feature representations by alternating a supervised learning phase and an unsupervised learning phase.  ...  This semi-supervised method helps us to learn the optimal representations of image and text features and apply Multi-modal DEC to HAR.  ... 
doi:10.1007/978-3-030-47426-3_67 fatcat:wqnltmtwencbrdvamml5cm4fqe

Medical Image Classification Based on Curriculam Learning

2019 International journal of recent technology and engineering  
Semi-Supervised Learning (SSL) is better than supervised learning as it eliminates labeling all images thus reducing computational cost and time.  ...  This paper is an attempt to apply SSL through Multi-Modal Curriculum Learning (MMCL) strategy over medical images. Through this, medical images can be categorized into normal and abnormal images.  ...  So semi-supervised learning is appropriate for medical applications. This requires only limited labelled images and with itself it can start the learning process.  ... 
doi:10.35940/ijrte.b1001.0782s219 fatcat:l725rxtlqjezfg6lfp6bg2646e

Multi-modal data fusion schemes for integrated classification of imaging and non-imaging biomedical data

Pallavi Tiwari, Satish Viswanath, George Lee, Anant Madabhushi
2011 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro  
These methods include (1) Generalized Embedding Concatenation (GEC), (2) Consensus Embedding (CE), (3) Semi-Supervised Multi-Kernel Graph Embedding (SeSMiK), and (4) Boosted Embedding Combination (BEC)  ...  With a wide array of multi-modal, multi-protocol, and multi-scale biomedical data available for disease diagnosis and prognosis, there is a need for quantitative tools to combine such varied channels of  ...  The predictor (metaclassifier) could be trained by a range of supervised, unsupervised, or semi-supervised learning strategies; the choice of training strategy usually being a function of the amount of  ... 
doi:10.1109/isbi.2011.5872379 pmid:25705325 pmcid:PMC4335721 dblp:conf/isbi/TiwariVLM11 fatcat:vno6hqss2jhyrlb7hn73ywqjqm

Guest Editorial: Ad Hoc Web Multimedia Analysis with Limited Supervision

Yahong Han, Yi Yang, Jingdong Wang
2015 Multimedia tools and applications  
/s11042-014-2018-y) paper proposes a semi-supervised multi-modal image classification method, which uses both the labeled and unlabeled examples for training.  ...  As unlabeled multimedia data always accompany multimodal examples on the social website, the "Markov Random Field Based Fusion for Supervised and Semi-supervised Multi-modal Image Classification" (10.1007  ... 
doi:10.1007/s11042-014-2419-y fatcat:hqct5eabprg75pocgful4sqn5e

Deep semi-supervised learning for brain tumor classification

Chenjie Ge, Irene Yu-Hua Gu, Asgeir Store Jakola, Jie Yang
2020 BMC Medical Imaging  
We propose to exploit deep semi-supervised learning to make full use of the unlabeled data.  ...  Deep CNN features were incorporated into a new graph-based semi-supervised learning framework for learning the labels of the unlabeled data, where a new 3D-2D consistent constraint is added to make consistent  ...  Acknowledgements The results in this paper are in part based upon the data generated by the TCGA Research Network:, and Multimodal Brain Tumor Image Segmentation Benchmark 2017  ... 
doi:10.1186/s12880-020-00485-0 pmid:32727476 fatcat:w3wwtdk6hvbg3f6o4ufdyxsxqy

Graph based multi-modality learning

Hanghang Tong, Jingrui He, Mingjing Li, Changshui Zhang, Wei-Ying Ma
2005 Proceedings of the 13th annual ACM international conference on Multimedia - MULTIMEDIA '05  
For semi-supervised learning, two different fusion schemes, namely linear form and sequential form, are proposed.  ...  To better understand the content of multimedia, a lot of research efforts have been made on how to learn from multi-modal feature.  ...  For semi-supervised learning, both classification and retrieval in QBK are considered.  ... 
doi:10.1145/1101149.1101337 dblp:conf/mm/TongHLZM05 fatcat:ux2tzibo6nbfrhr3pca2hxme6m

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.  ...  Throughout this survey, we further indicate that the critical components for this field go to collaboration, adversarial competition and fusion over multi-modal spaces.  ...  [21] proposed structured generative adversarial networks (SGANs) for semi-supervised image classification.  ... 
arXiv:2006.08159v1 fatcat:g4467zmutndglmy35n3eyfwxku

X-ModalNet: A Semi-Supervised Deep Cross-Modal Network for Classification of Remote Sensing Data [article]

Danfeng Hong, Naoto Yokoya, Gui-Song Xia, Jocelyn Chanussot, Xiao Xiang Zhu
2020 arXiv   pre-print
This paper addresses the problem of semi-supervised transfer learning with limited cross-modality data in remote sensing.  ...  Significantly, X-ModalNet generalizes well, owing to propagating labels on an updatable graph constructed by high-level features on the top of the network, yielding semi-supervised cross-modality learning  ...  Method Overview and Contributions Towards the aforementioned goals, a novel cross-modal DL framework is proposed in a semi-supervised fashion, called X-ModalNet, for RS image classification.  ... 
arXiv:2006.13806v1 fatcat:3b47auxsb5fzvc74uim5kkhwhm
« Previous Showing results 1 — 15 out of 15,680 results