Filters








2,167 Hits in 6.2 sec

Interactively Guiding Semi-Supervised Clustering via Attribute-Based Explanations [chapter]

Shrenik Lad, Devi Parikh
2014 Lecture Notes in Computer Science  
Semi-supervised approaches such as distance metric learning and constrained clustering thus leverage user-provided annotations indicating which pairs of images belong to the same cluster (must-link) and  ...  In particular, the clustering algorithm iteratively and actively queries a user with an image pair.  ...  To the best of our knowledge, ours is the first work on interactive semantic explanation-based clustering of images.  ... 
doi:10.1007/978-3-319-10599-4_22 fatcat:sm6a7xht2zewfn7tv3tgll4m4i

Normalized Cut Loss for Weakly-Supervised CNN Segmentation

Meng Tang, Abdelaziz Djelouah, Federico Perazzi, Yuri Boykov, Christopher Schroers
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training.  ...  Inspired by the general ideas in semi-supervised learning, we address these problems via a new principled loss function evaluating network output with criteria standard in "shallow" segmentation, e.g.  ...  Probably the simplest energy for shallow interactive image segmentation in [9] that also works for transductive semi-supervised learning (clustering) [55] combines hard constraints over seeds p ∈ Ω  ... 
doi:10.1109/cvpr.2018.00195 dblp:conf/cvpr/TangDPBS18 fatcat:pv5cejmx5ba4tnqt3wgxc4l55m

Normalized Cut Loss for Weakly-supervised CNN Segmentation [article]

Meng Tang and Abdelaziz Djelouah and Federico Perazzi and Yuri Boykov and Christopher Schroers
2018 arXiv   pre-print
Most recent semantic segmentation methods train deep convolutional neural networks with fully annotated masks requiring pixel-accuracy for good quality training.  ...  Inspired by the general ideas in semi-supervised learning, we address these problems via a new principled loss function evaluating network output with criteria standard in "shallow" segmentation, e.g.  ...  Probably the simplest energy for shallow interactive image segmentation in [9] that also works for transductive semi-supervised learning (clustering) [55] combines hard constraints over seeds p ∈ Ω  ... 
arXiv:1804.01346v1 fatcat:f3bjqinvarhaxl3543igaynzmi

Going Deeper into Semi-supervised Person Re-identification [article]

Olga Moskvyak, Frederic Maire, Feras Dayoub, Mahsa Baktashmotlagh
2021 arXiv   pre-print
To reduce the need for labeled data, we focus on a semi-supervised approach that requires only a subset of the training data to be labeled.  ...  We also propose a PartMixUp loss that improves the discriminative ability of learned part-based features for pseudo-labeling in semi-supervised settings.  ...  (semi-supervised BIL) and clustering of concatenated part-based embeddings (semi-supervised PB).  ... 
arXiv:2107.11566v1 fatcat:kpbuly4pzrgvblouuifuq6eoem

Weakly and Semi Supervised Human Body Part Parsing via Pose-Guided Knowledge Transfer [article]

Hao-Shu Fang, Guansong Lu, Xiaolin Fang, Jianwen Xie, Yu-Wing Tai, Cewu Lu
2018 arXiv   pre-print
Using these estimated results as additional training data, our semi-supervised model outperforms its strong-supervised counterpart by 6 mIOU on the PASCAL-Person-Part dataset, and we achieve state-of-the-art  ...  Human body part parsing, or human semantic part segmentation, is fundamental to many computer vision tasks.  ...  The semi-supervised result achieves 61.8 mIOU, which is on par with the results trained on ground-truth annotations.  ... 
arXiv:1805.04310v1 fatcat:3ccfdfdxu5d5pewhulahnh4sna

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
-- the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, cross-image relation, etc.  ...  However, the current segmentation algorithms mostly rely on the availability of pixel-level annotations, which are often expensive, tedious, and laborious.  ...  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

Weakly-Supervised Learning of a Deep Convolutional Neural Networks for Semantic Segmentation

Yanqing Feng, Lunwen Wang, Mengbo Zhang
2019 IEEE Access  
Deep convolutional neural networks (DCNNs) trained on the pixel-wise annotated images have dramatically improved the state-of-the-art in semantic segmentation.  ...  The decomposer is based on the orthogonal non-negative matrix factorization (NMF) technology.  ...  Therefore, the performance of segmentation methods based on object frame annotation is greatly improved compared with the image-level labels based segmentation method.  ... 
doi:10.1109/access.2019.2926972 fatcat:zabf3ovhhnfotbwntoiv7iwmlu

Semantics-Guided Clustering with Deep Progressive Learning for Semi-Supervised Person Re-identification [article]

Chih-Ting Liu, Yu-Jhe Li, Shao-Yi Chien, Yu-Chiang Frank Wang
2020 arXiv   pre-print
In extension, the generalization ability of our SGC-DPL is also verified in other tasks like vehicle re-ID or image retrieval with the semi-supervised setting.  ...  Assuming that such labeled and unlabeled training data share disjoint identity labels, we propose a novel framework of Semantics-Guided Clustering with Deep Progressive Learning (SGC-DPL) to jointly exploit  ...  Some works [9, 51] propose semi-supervised AP that utilizes the labeled data as additional constraints when clustering on the unlabeled data.  ... 
arXiv:2010.01148v1 fatcat:d7cojia47vdm3czddiz42j7kj4

Image Recognition and Analysis of Intrauterine Residues Based on Deep Learning and Semi-Supervised Learning

Tao Tao, Kan Liu, Li Wang, Haiying Wu
2020 IEEE Access  
Semi-supervised spectral clustering algorithm based on deep learning In semi-supervised clustering, the data information we get is generally data with class labels or paired constraint information.  ...  Among them, image-level annotation has the least cost, so most of the methods for semi-supervised learning based on weak annotations use image-level label.  ... 
doi:10.1109/access.2020.3020322 fatcat:mgkpfn7oozbp5actzq42bx5mtm

Exhaustive and Efficient Constraint Propagation: A Graph-Based Learning Approach and Its Applications

Zhiwu Lu, Yuxin Peng
2012 International Journal of Computer Vision  
This paper presents a novel pairwise constraint propagation approach by decomposing the challenging constraint propagation problem into a set of independent semi-supervised learning subproblems which can  ...  be solved in quadratic time using label propagation based on k-nearest neighbor graphs.  ...  This configuration of a twoclass semi-supervised learning problem is also suitable for soft constraints.  ... 
doi:10.1007/s11263-012-0602-z fatcat:aly6m6seo5gx7ebqujzpj6xbca

Video Shadow Detection via Spatio-Temporal Interpolation Consistency Training [article]

Xiao Lu, Yihong Cao, Sheng Liu, Chengjiang Long, Zipei Chen, Xuanyu Zhou, Yimin Yang, Chunxia Xiao
2022 arXiv   pre-print
Experimental results show that, even without video labels, our approach is better than most state of the art supervised, semi-supervised or unsupervised image/video shadow detection methods and other methods  ...  Our proposed approach is extensively validated on the ViSha dataset and a self-annotated dataset.  ...  ♯AF: number of annotated frames. Table 3 . 3 Comparison results of our method with SOTA methods. I.S.: Image-based supervised methods. I.U.: Image-based method without labels.  ... 
arXiv:2206.08801v1 fatcat:arobfwbq3zhshj7bh3riz3m4n4

Semi-supervised annotation of brushwork in paintings domain using serial combinations of multiple experts

Marchenko Yelizaveta, Chua Tat-Seng, Jain Ramesh
2006 Proceedings of the 14th annual ACM international conference on Multimedia - MULTIMEDIA '06  
Each expert focuses on the annotation of the currently available samples from its unlabeled pool using semi-supervised agglomerative clustering.  ...  In particular, we employ the serial multi-expert framework with semi-supervised clustering methods to perform the annotation of brushwork patterns.  ...  Existing methods for semi-supervised clustering fall into two general categories: constraint-based and distance-based.  ... 
doi:10.1145/1180639.1180752 dblp:conf/mm/YelizavetaCJ06a fatcat:biglhz2irrg77csy365ubr2zga

Image annotation with semi-supervised clustering

Ahmet Sayar, Fatos T. Yarman-Vural
2008 2008 IEEE 16th Signal Processing, Communication and Applications Conference  
Name, Last Name: AHMET SAYAR Signature : iii ABSTRACT IMAGE ANNOTATION WITH SEMI-SUPERVISED CLUSTERING Image annotation is defined as generating a set of textual words for a given image, learning from  ...  The side information provides a set of constraints in a semi-supervised K-means region clustering algorithm.  ...  Search based Semi-supervised Clustering: COP-KMeans Algorithm In search based semi-supervised clustering approach, the standard clustering algorithm is modified so as to adhere to the constraints provided  ... 
doi:10.1109/siu.2008.4632665 fatcat:o7l6jceccrbubhsek6mhe7rbrq

Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning [article]

Tsung-Wei Ke, Jyh-Jing Hwang, Stella X. Yu
2021 arXiv   pre-print
Weakly supervised segmentation requires assigning a label to every pixel based on training instances with partial annotations such as image-level tags, object bounding boxes, labeled points and scribbles  ...  We formulate weakly supervised segmentation as a semi-supervised metric learning problem, where pixels of the same (different) semantics need to be mapped to the same (distinctive) features.  ...  This work was supported, in part, by Berkeley Deep Drive and Berkeley AI Research Commons with Facebook.  ... 
arXiv:2105.00957v2 fatcat:fd52asxdmfgsbmmjs2jwfrf33y

Adaptive Labeling for Deep Learning to Hash

Huei-Fang Yang, Cheng-Hao Tu, Chu-Song Chen
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)  
It is applicable to both supervised and semi-supervised hash. Experimental results on standard benchmarks demonstrate the satisfactory performance of AdaLabelHash.  ...  As the label representations (or referred to as codewords in this work), are learned from data, semantically similar classes will be assigned with the codewords that are close to each other in terms of  ...  Semi-supervised Hashing via Self-training Leveraging the representation codewords, AdaLabel-Hash can be extended to semi-supervised learning, where the input data are provided with or without label annotations  ... 
doi:10.1109/cvprw.2019.00088 dblp:conf/cvpr/Yang0C19 fatcat:5xszme56zvewnjxnvgy7pf6p3e
« Previous Showing results 1 — 15 out of 2,167 results