Filters








6,063 Hits in 3.7 sec

Weakly- and Semi-Supervised Panoptic Segmentation [article]

Qizhu Li, Anurag Arnab, Philip H.S. Torr
2019 arXiv   pre-print
Furthermore, we present the first weakly-supervised results on Cityscapes for both semantic- and instance-segmentation.  ...  We present a weakly supervised model that jointly performs both semantic- and instance-segmentation -- a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for  ...  ., the EPSRC, Clarendon Fund, ERC grant ERC-2012-AdG 321162-HELIOS, EPRSRC grant Seebibyte EP/M013774/1 and EPSRC/MURI grant EP/N019474/1.  ... 
arXiv:1808.03575v3 fatcat:3hixm75un5ao7gkasdzi2o4ttq

Weakly- and Semi-supervised Panoptic Segmentation [chapter]

Qizhu Li, Anurag Arnab, Philip H. S. Torr
2018 Lecture Notes in Computer Science  
Furthermore, we present the first weakly-supervised results on Cityscapes for both semantic-and instance-segmentation.  ...  We present a weakly supervised model that jointly performs both semantic-and instance-segmentation -a particularly relevant problem given the substantial cost of obtaining pixel-perfect annotation for  ...  ., the EPSRC, Clarendon Fund, ERC grant ERC-2012-AdG 321162-HELIOS, EPRSRC grant Seebibyte EP/M013774/1 and EPSRC/MURI grant EP/N019474/1.  ... 
doi:10.1007/978-3-030-01267-0_7 fatcat:lqqibdtrynebhf3cjgjhj23voq

Budget-aware Semi-Supervised Semantic and Instance Segmentation [article]

Miriam Bellver, Amaia Salvador, Jordi Torres, Xavier Giro-i-Nieto
2019 arXiv   pre-print
With a very simple pipeline, we demonstrate that at low annotation budgets, semi-supervised methods outperform by a wide margin weakly-supervised ones for both semantic and instance segmentation.  ...  Another option are semi-supervised settings, that commonly leverage a few strong annotations and a huge number of unlabeled/weakly-labeled data.  ...  For semantic and instance segmentation, the use of weak labels as a cheaper supervision signal to train segmentation models has been extensively explored in the literature.  ... 
arXiv:1905.05880v2 fatcat:y2jvsgbsxze23lbzog3mpk2hzy

Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Anna Khoreva, Rodrigo Benenson, Jan Hosang, Matthias Hein, Bernt Schiele
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations.  ...  Overall, our weak supervision approach reaches ∼ 95% of the quality of the fully supervised model, both for semantic labelling and instance segmentation.  ...  Semantic labelling results Our approach is equally suitable (and effective) for weakly supervised instance segmentation as well as for semantic labelling.  ... 
doi:10.1109/cvpr.2017.181 dblp:conf/cvpr/KhorevaBH0S17 fatcat:4gvuzgxuhbcl5i5pwlrxai4dim

Simple Does It: Weakly Supervised Instance and Semantic Segmentation [article]

Anna Khoreva, Rodrigo Benenson, Jan Hosang, Matthias Hein, Bernt Schiele
2016 arXiv   pre-print
Semantic labelling and instance segmentation are two tasks that require particularly costly annotations.  ...  Overall, our weak supervision approach reaches ~95% of the quality of the fully supervised model, both for semantic labelling and instance segmentation.  ...  Semantic labelling results Our approach is equally suitable (and effective) for weakly supervised instance segmentation as well as for semantic labelling.  ... 
arXiv:1603.07485v2 fatcat:i3bsyd6jzbhlrj7zfw2xanr3wy

Weak Novel Categories without Tears: A Survey on Weak-Shot Learning [article]

Li Niu
2021 arXiv   pre-print
in weakly supervised learning.  ...  Therefore, weak-shot learning can also be treated as weakly supervised learning with auxiliary fully supervised categories.  ...  Besides, weakly-supervised object detection [4] , weakly-supervised semantic segmentation [40, 41, 43] , and weakly-supervised instance segmentation [71] have also been studied to bridge the gap between  ... 
arXiv:2110.02651v2 fatcat:hvvniqgukrdktmu4vjj6fefuqq

Weakly Supervised Learning of Instance Segmentation with Inter-pixel Relations [article]

Jiwoon Ahn, Sunghyun Cho, Suha Kwak
2019 arXiv   pre-print
This paper presents a novel approach for learning instance segmentation with image-level class labels as supervision.  ...  Our approach generates pseudo instance segmentation labels of training images, which are used to train a fully supervised model.  ...  Weakly Supervised Instance Segmentation: For instance segmentation, bounding boxes have been widely used as weak labels.  ... 
arXiv:1904.05044v3 fatcat:bxegbtkvvraapnofxiy4uaonii

Weakly Supervised Instance Segmentation by Deep Community Learning [article]

Jaedong Hwang, Seohyun Kim, Jeany Son, Bohyung Han
2020 arXiv   pre-print
This task is formulated as a combination of weakly supervised object detection and semantic segmentation, where individual objects of the same class are identified and segmented separately.  ...  We present a weakly supervised instance segmentation algorithm based on deep community learning with multiple tasks.  ...  Weakly Supervised Semantic Segmentation Weakly Supervised Semantic Segmentation (WSSS) is a task to estimate pixel-level semantic labels in an image based on image-level class labels only.  ... 
arXiv:2001.11207v3 fatcat:b5wdslbtezf65ezansgzdkisai

Weakly Supervised Deep Semantic Segmentation Using CNN and ELM with Semantic Candidate Regions

Xinying Xu, Guiqing Li, Gang Xie, Jinchang Ren, Xinlin Xie
2019 Complexity  
For fully supervised semantic segmentation, the task is achieved by a segmentation model trained using pixel-level annotations.  ...  Semantic inference of candidate regions is realized based on the relationship and neighborhood rough set associated with semantic labels.  ...  image-level labels weakly supervised image semantic segmentation algorithm method.  ... 
doi:10.1155/2019/9180391 fatcat:65uncqoqrnesrh3dxyutjdbumi

Weakly Supervised Learning of Instance Segmentation With Inter-Pixel Relations

Jiwoon Ahn, Sunghyun Cho, Suha Kwak
2019 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)  
This paper presents a novel approach for learning instance segmentation with image-level class labels as supervision.  ...  Our approach generates pseudo instance segmentation labels of training images, which are used to train a fully supervised model.  ...  Weakly Supervised Instance Segmentation: For instance segmentation, bounding boxes have been widely used as weak labels.  ... 
doi:10.1109/cvpr.2019.00231 dblp:conf/cvpr/AhnCK19 fatcat:eqn3gd2cxzhjjczbd5njlfyq2y

Multi-Evidence Filtering and Fusion for Multi-Label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning [article]

Weifeng Ge, Sibei Yang, Yizhou Yu
2018 arXiv   pre-print
weakly supervised semantic segmentation on MS-COCO, PASCAL VOC 2007 and PASCAL VOC 2012.  ...  In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation.  ...  pixel-wise labels Y I = [y 1 , y 2 , ..., y P ] T , and then use these labels to assist weakly supervised object detection, semantic segmentation and multi-label image classification.  ... 
arXiv:1802.09129v1 fatcat:mgoa2e4ysncpbgnif7axsqrog4

Multi-evidence Filtering and Fusion for Multi-label Classification, Object Detection and Semantic Segmentation Based on Weakly Supervised Learning

Weifeng Ge, Sibei Yang, Yizhou Yu
2018 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition  
weakly supervised semantic segmentation on MS-COCO, PASCAL VOC 2007 and PASCAL VOC 2012.  ...  In this paper, we propose a novel weakly supervised curriculum learning pipeline for multi-label object recognition, detection and semantic segmentation.  ...  pixel-wise labels Y I = [y 1 , y 2 , ..., y P ] T , and then use these labels to assist weakly supervised object detection, semantic segmentation and multi-label image classification.  ... 
doi:10.1109/cvpr.2018.00139 dblp:conf/cvpr/GeYY18 fatcat:dkwcvetog5gatoya2aqwrucvoi

SegGroup: Seg-Level Supervision for 3D Instance and Semantic Segmentation [article]

An Tao, Yueqi Duan, Yi Wei, Jiwen Lu, Jie Zhou
2022 arXiv   pre-print
Most existing point cloud instance and semantic segmentation methods rely heavily on strong supervision signals, which require point-level labels for every point in the scene.  ...  In this paper, we discover that the locations of instances matter for both instance and semantic 3D scene segmentation.  ...  Weakly-supervised Image Segmentation Many works have been proposed for weakly-supervised image segmentation, where image-level supervision [39] - [43] and bounding box supervision [44] - [46] are  ... 
arXiv:2012.10217v4 fatcat:mo3j5ujntvg3rer6kiel5e7qjm

Label-Efficient Hybrid-Supervised Learning for Medical Image Segmentation

Junwen Pan, Qi Bi, Yanzhan Yang, Pengfei Zhu, Cheng Bian
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
However, these approaches only concentrate on the supervision inconsistency between strongly- and weakly-annotated instances but ignore the instance inconsistency inside the weakly-annotated instances,  ...  To address this problem, we propose a novel label-efficient hybrid-supervised framework, which considers each weakly-annotated instance individually and learns its weight guided by the gradient direction  ...  and 61925602, the Applied Basic Research Program of Qinghai under Grant 2019-ZJ-7017.  ... 
doi:10.1609/aaai.v36i2.20098 fatcat:hjxrhn4vb5hvth5ufygxiycu44

Box2Mask: Weakly Supervised 3D Semantic Instance Segmentation Using Bounding Boxes [article]

Julian Chibane, Francis Engelmann, Tuan Anh Tran, Gerard Pons-Moll
2022 arXiv   pre-print
In this work, we look at weakly-supervised 3D semantic instance segmentation. The key idea is to leverage 3D bounding box labels which are easier and faster to annotate.  ...  3D instance segmentation masks.  ...  Semantic instance segmentation scores on ScanNet val. trained with missing box labels (left) and noisy box labels (right).  ... 
arXiv:2206.01203v2 fatcat:ea7r3w3i5nayhe22plh35mqpku
« Previous Showing results 1 — 15 out of 6,063 results