A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Filters
Unsupervised Segmentation for Terracotta Warrior with Seed-Region-Growing CNN(SRG-Net)
[article]
2021
arXiv
pre-print
Preserved Fulltext
There are few pieces of researches concentrating on unsupervised point cloud part segmentation. In this paper, we present SRG-Net for 3D point clouds of terracotta warriors to address these problems. ...
Then we present a supervised segmentation and unsupervised reconstruction networks to learn the characteristics of 3D point clouds. ...
Acknowledgments
Disclosures The authors declare no conflicts of interest. ...
arXiv:2107.13167v1
fatcat:c6xqkf5o2vaodm44cp3umcisoq
Unsupervised Segmentation for Terracotta Warrior Point Cloud (SRG-Net)
[article]
2022
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
Other Versions
There are few pieces of researches concentrating on unsupervised point cloud part segmentation. In this paper, we present SRG-Net for 3D point clouds of terracotta warriors to address these problems. ...
Then we present a supervised segmentation and unsupervised reconstruction networks to learn the characteristics of 3D point clouds. ...
Komodakis [2017]) for every point cloud.Unlike the supervised problem, our unsupervised method solves two sub-problems: prediction of cluster labels with fixed network parameters and training of network ...
arXiv:2012.00433v2
fatcat:ypjb7j5cdrc5bosfvvvsiiy4fy
Unsupervised Learning of Image Segmentation Based on Differentiable Feature Clustering
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. ...
First, we propose a novel end-to-end network of unsupervised image segmentation that consists of normalization and an argmax function for differentiable clustering. ...
Abstract-The usage of convolutional neural networks (CNNs) for unsupervised image segmentation was investigated in this study. ...
arXiv:2007.09990v1
fatcat:omgrrr57jffo7jzzp2bumy4mwq
Various OCT Segmentation and Classification Techniques
2020
International Journal of Information Systems and Computer Sciences
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2022; you can also visit the original URL.
The file type is application/pdf.
This paper describes different methods for the analysis of OCT images and their comparison. In this paper various models of image segmentation and classification are discussed. ...
Optical coherence tomography is a non-intrusive method for the image. OCT is a well-known modality of detecting and inventing ocular disease on time. ...
Unsupervised research will expand our understanding of the original pathway of disease physiology. Unsupervised learning are divided into • Clustering: to discover similarities and differences. ...
doi:10.30534/ijiscs/2020/05932020
fatcat:2ryhljqlbraztospd3amkt6l4q
Identifying and Categorizing Anomalies in Retinal Imaging Data
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We detect and categorize candidates for anomaly findings untypical for the observed data. A deep convolutional autoencoder is trained on healthy retinal images. ...
The identification and quantification of markers in medical images is critical for diagnosis, prognosis and management of patients in clinical practice. ...
Acknowledgments This work funded by the Austrian Federal Ministry of Science, Research and Economy, and the FWF (I2714-B31). A Tesla K40 used for this research was donated by the NVIDIA Corporation. ...
arXiv:1612.00686v1
fatcat:gadi553t6jgizacrb6nrpiwcn4
Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
[article]
2020
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
For this task, we present a novel adaptive graph convolutional network with attention graph clustering (GCAGC). ...
Co-saliency detection aims to discover the common and salient foregrounds from a group of relevant images. ...
Conclusion This paper has presented an adaptive graph convolutional network with attention graph clustering for co-saliency detection, mainly including two key designs: an AGCN and an AGCM. ...
arXiv:2003.06167v1
fatcat:viapz273g5cv7lzln7x76pfuxq
Efficient Convolutional Neural Network with Binary Quantization Layer
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Our segmentation proposes visually and semantically coherent image segments. ...
In this paper we introduce a novel method for segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). ...
Then, the graph is partitioned into a set of sub-graphs corresponding to image segments by minimizing a cost function. ...
arXiv:1611.06764v1
fatcat:fzpcftcn35hvtit7d4rp5jqhye
CNN-aware Binary Map for General Semantic Segmentation
[article]
2016
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
In this paper we introduce a novel method for general semantic segmentation that can benefit from general semantics of Convolutional Neural Network (CNN). ...
Our segmentation proposes visually and semantically coherent image segments. ...
Then, the graph is partitioned into a set of sub-graphs corresponding to image segments by minimizing a cost function. ...
arXiv:1609.09220v1
fatcat:6ldskhhnefbypgofiqwuhcjdny
Texture segmentation with Fully Convolutional Networks
[article]
2017
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
We take advantage of these findings to develop a method that is evaluated on a series of supervised and unsupervised experiments and improve the state of the art on the Prague texture segmentation datasets ...
We demonstrate that Fully Convolutional Networks can learn from repetitive patterns to segment a particular texture from a single image or even a part of an image. ...
The images are split into four sub images of size 288 × 288. ...
arXiv:1703.05230v1
fatcat:ptd55i6ydzgzho2hlnitdm6344
Learning to Cluster Faces on an Affinity Graph
[article]
2019
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Specifically, we propose a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters. ...
A key challenge lies in the complex variations of cluster patterns, which make it difficult for conventional clustering methods to meet the needed accuracy. ...
Extensive analysis further demonstrate the effectiveness of our framework. Figure 2 : 2 Overview of graph detection and segmentation for clustering. ...
arXiv:1904.02749v2
fatcat:sx5mffduszdg5ct6ifped6evae
Capturing implicit hierarchical structure in 3D biomedical images with self-supervised hyperbolic representations
[article]
2021
arXiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2020 pre-print arXiv:2012.01644v1 fatcat:bqblw7cqnbfwfnvr7igjbh7fdiOther Versions
We consider the task of representation learning for unsupervised segmentation of 3D voxel-grid biomedical images. ...
We propose utilizing a 3D hyperbolic variational autoencoder with a novel gyroplane convolutional layer to map from the embedding space back to 3D images. ...
Unsupervised segmentation of 3d medical images based on clustering and
deep representation learning. ...
arXiv:2012.01644v3
fatcat:fjwughxgonbzdmxeiiqhuvz26i
Learning to Cluster Faces on an Affinity Graph
2019
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf.
Specifically, we propose a framework based on graph convolutional network, which combines a detection and a segmentation module to pinpoint face clusters. ...
A key challenge lies in the complex variations of cluster patterns, which make it difficult for conventional clustering methods to meet the needed accuracy. ...
Extensive analysis further demonstrate the effectiveness of our framework. Figure 2 : 2 Overview of graph detection and segmentation for clustering. ...
doi:10.1109/cvpr.2019.00240
dblp:conf/cvpr/YangZCYLL19
fatcat:fk4ykuipgjacblni6qhfumlgpq
Deep Object Co-Segmentation via Spatial-Semantic Network Modulation
2020
PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf.
The outputs of the two modulators manipulate the multi-resolution features by a shift-and-scale operation so that the features focus on segmenting co-object regions. ...
The spatial modulator captures the correlations of image feature descriptors via unsupervised learning. ...
Acknowledgments This work is supported in part by National Major Project of China for New Generation of AI (No. 2018AAA0100400), in part by the Natural Science Foundation of China under Grant nos. 61876088 ...
doi:10.1609/aaai.v34i07.6977
fatcat:7zrzv5kjwbdzjphqdnnslrrmmy
Topological Feature Extraction and Visualization of Whole Slide Images using Graph Neural Networks
[article]
2020
bioRxiv
pre-print
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
Here, we review two promising methods for capturing macro and micro architecture of histology images, Graph Neural Networks, which contextualize patch level information from their neighbors through message ...
Deep learning approaches to digital pathology typically extract information from sub-images (patches) and treat the sub-images as independent entities, ignoring contributing information from vital large-scale ...
Acknowledgements
Preprint of an article published in Pacific Symposium on Biocomputing © 2021 World Scientific Publishing Co., Singapore, http://psb.stanford.edu/ ...
doi:10.1101/2020.08.01.231639
fatcat:vi5f5a5exnbypeeo4smjr23ke4
Multi-Faceted Hierarchical Image Segmentation Taxonomy ( MFHIST)
2021
IEEE Access
Preserved Fulltext
A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf.
INDEX TERMS Literature survey, multi-faceted taxonomy, image segmentation, region based, semantic based. ...
The paper gives an illustration of populating MFHIST, to provide the reader a quick grasp of few important state-of-art image segmentation research works and their adaptations. ...
Very recently, Andrej Karpathy et.al. in [46] mentions researching on ''dense annotations of image segments based on combination of convolutional neural networks (for image regions) and recurrent neural ...
doi:10.1109/access.2021.3055678
fatcat:r3aaee4vrbgqhdzlb6qc5vkefy
« Previous
Showing results 1 — 15 out of 3,490 results