Filters








3,431 Hits in 3.9 sec

Discovering Latent Classes for Semi-Supervised Semantic Segmentation [article]

Olga Zatsarynna, Johann Sawatzky, Juergen Gall
2020 arXiv   pre-print
This paper studies the problem of semi-supervised semantic segmentation.  ...  On unlabeled images, we predict a probability map for latent classes and use it as a supervision signal to learn semantic segmentation.  ...  In this work, we propose an approach for semi-supervised semantic segmentation that does not discard any information.  ... 
arXiv:1912.12936v3 fatcat:caa2ip7qtnahpj5iwfubl5fdnu

Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP [article]

Daniil Pakhomov, Sanchit Hira, Narayani Wagle, Kemar E. Green, Nassir Navab
2021 arXiv   pre-print
We introduce a method that allows to automatically segment images into semantically meaningful regions without human supervision.  ...  In cases where semantic regions might be hard for human to define and consistently label, our method is still able to find meaningful and consistent semantic classes.  ...  Example of semantic classes discovered by clustering features from different layers for OpenEDS eye segmentation dataset.  ... 
arXiv:2107.12518v2 fatcat:xkj4pjigrnegxeyv34xrj4oaeq

PiCoCo: Pixelwise Contrast and Consistency Learning for Semi-Supervised Building Footprint Segmentation

Jian Kang, Zhirui Wang, Ruoxin Zhu, Xian Sun, Ruben Fernandez-Beltran, Antonio J Plaza
2021 IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing  
semi-supervised semantic segmentation methods.  ...  Semi-Supervised Semantic Segmentation Semi-supervised semantic segmentation is aimed at learning the segmentation models based on both labeled and unlabeled images [43] - [45] .  ... 
doi:10.1109/jstars.2021.3119286 fatcat:7xfdzrevnjeehbqpw5z2k45xq4

Mining Latent Classes for Few-shot Segmentation [article]

Lihe Yang, Wei Zhuo, Lei Qi, Yinghuan Shi, Yang Gao
2021 arXiv   pre-print
Few-shot segmentation (FSS) aims to segment unseen classes given only a few annotated samples.  ...  Our method aims to alleviate this problem and enhance the feature embedding on latent novel classes. In our work, we propose a novel joint-training framework.  ...  Motivated by this, we boost the few-shot segmentation via mining latent objects from the backgrounds. Semi-/self-supervised Learning.  ... 
arXiv:2103.15402v3 fatcat:zksnaw3pqnaj5boieyqpdf6vsm

Latent semantic modeling for slot filling in conversational understanding

Gokhan Tur, Asli Celikyilmaz, Dilek Hakkani-Tur
2013 2013 IEEE International Conference on Acoustics, Speech and Signal Processing  
Our method decomposes the task into two steps: latent n-gram clustering using a semi-supervised latent Dirichlet allocation (LDA) and sequence tagging for learning semantic structures in a CU system.  ...  In this paper, we propose a new framework for semantic template filling in a conversational understanding (CU) system.  ...  Experimental results for exploiting semi-supervised latent semantic information.  ... 
doi:10.1109/icassp.2013.6639285 dblp:conf/icassp/TurCH13 fatcat:qqqqwo7rrvdbfmlka7agooovme

Semi-automatic audio semantic concept discovery for multimedia retrieval

Yipei Wang, Shourabh Rawat, Florian Metze
2014 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)  
To address these issues, we propose a semi-automatic framework to discover the semantic concepts. We limit ourselves in audio modality here.  ...  Previous work explored semantic concepts for content analysis to assist retrieval.  ...  CONCLUSION In this paper, we present a novel framework to discover audio semantic concepts semi-automatically.  ... 
doi:10.1109/icassp.2014.6853822 dblp:conf/icassp/WangRM14a fatcat:h5od6ae3njadbbut3czjlavwgi

Unsupervised Domain Adaptation in Semantic Segmentation: a Review [article]

Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh
2020 arXiv   pre-print
The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.  ...  This task is attracting a wide interest, since semantic segmentation models require a huge amount of labeled data and the lack of data fitting specific requirements is the main limitation in the deployment  ...  We start this section by presenting some weakly-and semi-supervised learning methods for semantic segmentation.  ... 
arXiv:2005.10876v1 fatcat:7t5v6qibxnfcxhwtohqqunhd2u

Decoupled Deep Neural Network for Semi-supervised Semantic Segmentation [article]

Seunghoon Hong, Hyeonwoo Noh, Bohyung Han
2015 arXiv   pre-print
We propose a novel deep neural network architecture for semi-supervised semantic segmentation using heterogeneous annotations.  ...  It facilitates to reduce search space for segmentation effectively by exploiting class-specific activation maps obtained from bridging layers.  ...  Conclusion We proposed a novel deep neural network architecture for semi-supervised semantic segmentation with heterogeneous annotations, where classification and segmentation networks are decoupled for  ... 
arXiv:1506.04924v2 fatcat:kdljwoets5h53jes3iwph75ypy

Unsupervised Domain Adaptation in Semantic Segmentation: A Review

Marco Toldo, Andrea Maracani, Umberto Michieli, Pietro Zanuttigh
2020 Technologies  
The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation.  ...  This task is attracting a wide interest since semantic segmentation models require a huge amount of labeled data and the lack of data fitting specific requirements is the main limitation in the deployment  ...  We start this section by presenting some weakly-and semi-supervised learning methods for semantic segmentation.  ... 
doi:10.3390/technologies8020035 fatcat:qzgjjiw5p5bldk76mh3s3pwlfq

Learning Saliency Propagation for Semi-Supervised Instance Segmentation

Yanzhao Zhou, Xin Wang, Jianbin Jiao, Trevor Darrell, Fisher Yu
2020 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
The results show our method establishes new states of the art for semi-supervised instance segmentation. 1  ...  Instance segmentation is a challenging task for both modeling and annotation. Due to the high annotation cost, modeling becomes more difficult because of the limited amount of supervision.  ...  Note that this is different from previous works that utilize MIL to discover class-specific responses in the image for semantic segmentation [29] .  ... 
doi:10.1109/cvpr42600.2020.01032 dblp:conf/cvpr/ZhouWJDY20 fatcat:qcak6ujxt5dolca4dtudmuezkm

Attribute Learning for Understanding Unstructured Social Activity [chapter]

Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong
2012 Lecture Notes in Computer Science  
To solve this problem, we (1) contribute an unstructured social activity attribute (USAA) dataset with both visual and audio attributes, (2) introduce the concept of semi-latent attribute space and (3)  ...  Recently, attribute learning has emerged as a promising paradigm for transferring learning to sparsely labelled classes in object or single-object short action classification.  ...  Discovering and learning those discriminative yet latent attributes thus becomes the key.  ... 
doi:10.1007/978-3-642-33765-9_38 fatcat:nsltcn7qyjcwfmlct67ce6h5du

Factorised spatial representation learning: application in semi-supervised myocardial segmentation [article]

Agisilaos Chartsias, Thomas Joyce, Giorgos Papanastasiou, Scott Semple, Michelle Williams, David Newby, Rohan Dharmakumar, Sotirios A. Tsaftaris
2018 arXiv   pre-print
We demonstrate the proposed method's utility in a semi-supervised setting: we use very few labelled images together with many unlabelled images to train a myocardium segmentation neural network.  ...  In this paper, we propose a methodology of latent space factorisation relying on the cycle-consistency principle.  ...  We also thank NVIDIA Corporation for donating a Titan X GPU.  ... 
arXiv:1803.07031v2 fatcat:emcaprxdxrejfgo525kgqyjz2m

Learning Multimodal Latent Attributes

Yanwei Fu, Timothy M. Hospedales, Tao Xiang, Shaogang Gong
2014 IEEE Transactions on Pattern Analysis and Machine Intelligence  
model for learning multi-modal semi-latent attributes, which dramatically reduces requirements for an exhaustive accurate attribute ontology and expensive annotation effort.  ...  To solve this problem, we (1) introduce a concept of semi-latent attribute space, expressing user-defined and latent attributes in a unified framework, and (2) propose a novel scalable probabilistic topic  ...  Semi-latent semantic attribute space A p dimensional metric space where p ud dimensions encode manually specified semantic properties, and p la dimensions encode latent semantic properties determined by  ... 
doi:10.1109/tpami.2013.128 pmid:24356351 fatcat:tlchipuvl5evflsw6ewqs2oqyu

A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction [article]

Wei Shen, Zelin Peng, Xuehui Wang, Huayu Wang, Jiazhong Cen, Dongsheng Jiang, Lingxi Xie, Xiaokang Yang, Qi Tian
2022 arXiv   pre-print
and noisy supervision) and supplemented by the types of segmentation problems (including semantic segmentation, instance segmentation and panoptic segmentation).  ...  Finally, we share our opinions about the future research directions for label-efficient deep segmentation.  ...  Semi-supervised Segmentation Semi-supervised semantic segmentation In this section, we review the methods for semi-supervised semantic segmentation, where only a small fraction of training images is  ... 
arXiv:2207.01223v1 fatcat:i7rgpxrfkrdbfm4effjdcjjr24

Adversarial Learning for Semi-Supervised Semantic Segmentation [article]

Wei-Chih Hung, Yi-Hsuan Tsai, Yan-Ting Liou, Yen-Yu Lin, Ming-Hsuan Yang
2018 arXiv   pre-print
We propose a method for semi-supervised semantic segmentation using an adversarial network.  ...  In addition, the fully convolutional discriminator enables semi-supervised learning through discovering the trustworthy regions in predicted results of unlabeled images, thereby providing additional supervisory  ...  Figure 1 : Overview of the proposed system for semi-supervised semantic segmentation.  ... 
arXiv:1802.07934v2 fatcat:vzcurbdrgzdfflikr6sdjup6um
« Previous Showing results 1 — 15 out of 3,431 results