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
Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision
[article]
2021
arXiv
pre-print
Preserved Fulltext
Other Versions
In this paper, we study the semi-supervised semantic segmentation problem via exploring both labeled data and extra unlabeled data. ...
The pseudo one-hot label map, output from one perturbed segmentation network, is used to supervise the other segmentation network with the standard cross-entropy loss, and vice versa. ...
We evaluate the segmentation performance using mean Intersection-over-Union (mIoU) metric. For all partition protocols, we report results on the ...
arXiv:2106.01226v2
fatcat:stmh6tu4pbedpb3siioq63icn4
Semi-supervision semantic segmentation with uncertainty-guided self cross supervision
[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
As a powerful way of realizing semi-supervised segmentation, the cross supervision method learns cross consistency based on independent ensemble models using abundant unlabeled images. ...
However, the wrong pseudo labeling information generated by cross supervision would confuse the training process and negatively affect the effectiveness of the segmentation model. ...
Conclusions In this paper, we propose a new cross supervision based semi-supervised semantic segmentation approach, uncertaintyguided self cross supervision. ...
arXiv:2203.05118v2
fatcat:5n3jqg2xpbakhipq234svlgkpi
A Survey on Label-efficient Deep Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction
[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.
and noisy supervision) and supplemented by the types of segmentation problems (including semantic segmentation, instance segmentation and panoptic segmentation). ...
-- the current methods are mostly based on heuristic priors, such as cross-pixel similarity, cross-label constraint, cross-view consistency, cross-image relation, etc. ...
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
Digging into Pseudo Label: a Low-budget Approach for Semi-Supervised Semantic Segmentation
2020
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 2020; you can also visit the original URL.
The file type is application/pdf.
Although semi-supervised learning for image classification has been extensively studied in some cases, semantic segmentation with limited data has only recently gained attention. ...
On standard benchmark PASCAL VOC 2012 for semi-supervised semantic segmentation, the proposed approach gains fresh state-of-the-art performance. ...
Figure 5 and Table 1 compare our method with the recent weakly supervised and semi-supervised semantic segmentation methods. ...
doi:10.1109/access.2020.2975022
fatcat:3gicsfklwbc7deurtryl655ovy
UCC: Uncertainty guided Cross-head Co-training for Semi-Supervised Semantic Segmentation
[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.
We present a novel learning framework called Uncertainty guided Cross-head Co-training (UCC) for semi-supervised semantic segmentation. ...
Our approach significantly outperforms other state-of-the-art semi-supervised semantic segmentation methods. ...
Semi-Supervised Semantic Segmentation. ...
arXiv:2205.10334v1
fatcat:nxkf2ct6cngpvcaocw5mn5kyoe
A Simple Baseline for Semi-supervised Semantic Segmentation with Strong Data Augmentation
[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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Inspired by the success of semi-supervised learning methods in image classification, here we propose a simple yet effective semi-supervised learning framework for semantic segmentation. ...
We demonstrate that the devil is in the details: a set of simple design and training techniques can collectively improve the performance of semi-supervised semantic segmentation significantly. ...
Our Method
Semi-supervised Semantic Segmentation In this section, we introduce our simple semi-supervised learning framework for semantic segmentation. ...
arXiv:2104.07256v4
fatcat:ajhsvgtwhrdpbf6cxrujvfsqju
Mask-based Data Augmentation for Semi-supervised Semantic Segmentation
[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 2021; you can also visit the original URL.
The file type is application/pdf.
Semi-supervised learning algorithms address this issue by utilizing unlabeled data and so reduce the amount of labeled data needed for training. ...
Semantic segmentation using convolutional neural networks (CNN) is a crucial component in image analysis. ...
Pseudo labeling. Pseudo labeling is a commonly used technique for semi-supervised learning in semantic segmentation. Feng et al. ...
arXiv:2101.10156v1
fatcat:nfakhuguk5bhvbfukgtxekvirq
Semi-supervised Semantic Segmentation with Error Localization Network
[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
This paper studies semi-supervised learning of semantic segmentation, which assumes that only a small portion of training images are labeled and the others remain unlabeled. ...
ELN enables semi-supervised learning to be robust against inaccurate pseudo labels by disregarding label noises during training and can be naturally integrated with self-training and contrastive learning ...
Semi-supervised semantic segmentation. Attempts to reduce the cost by applying a semi-supervised learning scheme have been studied intensely. ...
arXiv:2204.02078v3
fatcat:ct75uaz75zesndt3amal7jk6wi
SSPC-Net: Semi-supervised Semantic 3D Point Cloud Segmentation Network
[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 2021; you can also visit the original URL.
The file type is application/pdf.
Other Versions
Finally, we employ the cross-entropy loss to train the semantic segmentation network with the labels of the supervised superpoints and the pseudo labels of the unsupervised superpoints. ...
Experiments on various datasets demonstrate that our semi-supervised segmentation method can achieve better performance than the current semi-supervised segmentation method with fewer annotated 3D points ...
However, in this paper, we focus on the semi-supervised point cloud semantic segmentation. Semi-/Weakly supervised deep learning on 3D point clouds. ...
arXiv:2104.07861v3
fatcat:77a6f2szqzauhn52qwofx54m7q
Semi-Supervised Remote Sensing Image Semantic Segmentation via Consistency Regularization and Average Update of Pseudo-Label
2020
Remote Sensing
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.
and strong labels to train semantic segmentation network. ...
This paper proposes a method for remote sensing image segmentation based on semi-supervised learning. ...
However, too little work has been devoted to semi-supervised semantic image segmentation. Most existing methods need large amounts of data with pixel-level labels. ...
doi:10.3390/rs12213603
fatcat:jtg6jxaebvebpm35yunq5idziq
Semi-supervised Domain Adaptation for Semantic Segmentation
[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 2021; you can also visit the original URL.
The file type is application/pdf.
We propose a novel and effective two-step semi-supervised dual-domain adaptation (SSDDA) approach to address both cross- and intra-domain gaps in semantic segmentation. ...
To cope with these limitations, both unsupervised domain adaptation (UDA) with full source supervision but without target supervision and semi-supervised learning (SSL) with partial supervision have been ...
of our proposed approach to semi-supervised dual-domain adaptation for semantic segmentation. ...
arXiv:2110.10639v1
fatcat:fx2dojvzfbczvmpvwqhl2i6m2i
Learning Self-supervised Low-Rank Network for Single-Stage Weakly and Semi-supervised Semantic Segmentation
2022
International Journal of Computer Vision
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.
Note that this fulltext copy is not of the "primary" version of this work. The version it corresponds to is:
2022 pre-print arXiv:2203.10278v1 fatcat:4o5o2ctrlffhfjvafuhkmbs3ay
Semantic segmentation with limited annotations, such as weakly supervised semantic segmentation (WSSS) and semi-supervised semantic segmentation (SSSS), is a challenging task that has attracted much attention ...
The SLRNet uses cross-view self-supervision, that is, it simultaneously predicts several complementary attentive LR representations from different views of an image to learn precise pseudo-labels. ...
Semi-Supervised Semantic Segmentation Generally, in semi-supervised learning, only a small subset of training images are assumed to have annotations, and a large number of unlabeled data are exploited ...
doi:10.1007/s11263-022-01590-z
fatcat:32mtwzeryfcztkxglai5xx2tfi
n-CPS: Generalising Cross Pseudo Supervision to n Networks for Semi-Supervised Semantic Segmentation
[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
We present n-CPS - a generalisation of the recent state-of-the-art cross pseudo supervision (CPS) approach for the task of semi-supervised semantic segmentation. ...
To the best of our knowledge, n-CPS paired with CutMix outperforms CPS and sets the new state-of-the-art for Pascal VOC 2012 with (1/16, 1/8, 1/4, and 1/2 supervised regimes) and Cityscapes (1/16 supervised ...
The proposed method generalises the cross pseudo supervision (CPS) approach for semi-supervised semantic segmentation. ...
arXiv:2112.07528v4
fatcat:zvwd3ltvczgtzch3w37yahaxoe
Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
[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 2021; you can also visit the original URL.
The file type is application/pdf.
This paper addresses semi-supervised semantic segmentation by exploiting a small set of images with pixel-level annotations (strong supervisions) and a large set of images with only image-level annotations ...
In particular, for the generated pixel-level noisy labels from weak supervisions by Class Activation Map (CAM), we train a clean segmentation model with strong supervisions to detect the clean labels from ...
We believe that semi-supervised semantic segmentation can be formulated as a problem of learning with pixel-level label noise. ...
arXiv:2103.14242v1
fatcat:kwhr3d5kgjbrlbvvnhrkd4jdsm
Self Semi Supervised Neural Architecture Search for Semantic Segmentation
[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
In this paper, we propose a Neural Architecture Search strategy based on self supervision and semi-supervised learning for the task of semantic segmentation. ...
the structure of the unlabeled data with semi-supervised learning. ...
More recently, another example of holistic approach, using Cross Pseudo supervision [14] on the task of semantic segmentation, have shown state-of-the-art results. ...
arXiv:2201.12646v2
fatcat:dqasniazhjhclm2kzjx6vwfimy
« Previous
Showing results 1 — 15 out of 4,190 results