Semi Supervised Semantic Segmentation Using Generative Adversarial Network

By Nasim Souly, Concetto Spampinato, Mubarak Shah. IEEE International Conference on Computer Vision, 2017

473 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/6c7bdab6e39a6045f4700efb5b09a8c5e646e7c9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Semi-Supervised Semantic Segmentation with Cross Pseudo Supervision (2021, methodology): “For example, the GANbased methods [13, 25, 29], use the discriminator learned for distinguishing the predictions and the ground-truth segmentation to select high-confident segmentation predictions on unlabeled images as pseudo segmentation.”
You Only Need Adversarial Supervision for Semantic Image Synthesis (2020, background): “Segmentation-based discriminators have been shown to improve semantic segmentation (Souly et al., 2017) and unconditional image synthesis (Schönfeld et al.”
Naive-Student: Leveraging Semi-Supervised Learning in Video Sequences for Urban Scene Segmentation (2020, background): “some human-annotated images and abundant pseudolabeled [42,72,34,3] video sequences. Semi-supervised learning has been widely applied to several computer vision tasks, including semantic segmentation [57,19,59,31,80,35,81,73,96], object detection [68,76,64], instance segmentation [35,60], panoptic s”
Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization (2021, methodology): “Conceptually, [84] trains a generator together with a pixel-wise discriminator network to perform segmentation, while [41, 17, 52] learn to generate synthetic 3D scenes by matching distributions of real and rendered imagery.”
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency (2019, methodology): “Only two previous works [15], [34] have considered true semi-supervised learning for semantic segmentation, which requires having a small subset of fully-labeled samples along with a larger set of completely annotation-free images.”
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation (2022, unknown): “Therefore, several methods aim to reduce the annotation burden such as weakly-supervised learning [14, 61, 93], semi-supervised learning [17, 27, 35, 53], and unsupervised domain adaption (UDA) [26, 28, 59, 67, 92].”
Semi-Supervised and Unsupervised Deep Visual Learning: A Survey (2022, methodology): “…UL for image classiﬁcation, and adapt techniques such as consistency regularization [31], [178], [179], [180], self-training [32], [168], [174], [181], [182], [183], [184], GAN frameworks [185], [186] in SSL, or contrastive learning [187], [188], [189], [190] in UL to learn from unlabeled images.”
DatasetGAN: Efficient Labeled Data Factory with Minimal Human Effort (2021, background): “Semi-Supervised Learning: Given a large set of unlabeled images and a small set of annotated images, semisupervised approaches [37, 47, 22, 40, 27] aim to learn better segmentation networks than with supervised data alone.”
Self-Supervised Representation Learning for Remote Sensing Image Change Detection Based on Temporal Prediction (2020, background): “Recently, generative adversarial networks (GAN) have gained in popularity, being adopted for many tasks such as object tracking [22], image generation [23,24], and semantic segmentation [25].”
VITAL: VIsual Tracking via Adversarial Learning (2018, background): “series of works on network training [1, 40, 18] and computer vision applications, such as image generation [62], image stylization [26], object detection [58], and semantic segmentation [53].”
A Survey on Deep Semi-Supervised Learning (2021, methodology): “In this survey, we mainly discuss the methods applied to image classification since these methods can be extended to other applications, such as [49] applied consistency training to object detection, [50] modified Semi-GANs to fit the scenario of semantic segmentation.”
Semi-Supervised Semantic Segmentation With Cross-Consistency Training (2020, methodology): “Generative Adversarial Networks (GANs) were also adapted for SSL setting [49, 23] by extending the generic GAN framework to pixel-level predictions.”
PseudoSeg: Designing Pseudo Labels for Semantic Segmentation (2020, methodology): “Early methods utilize a GAN-based model either to generate additional training data (Souly et al., 2017) or to learn a discriminator between the prediction and the ground truth mask (Hung et al., 2018; Mittal et al., 2019).”
Image Segmentation Using Deep Learning: A Survey (2020, unknown): “[101] proposed semi-weakly supervised semantic segmentation using GANs.”
Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation (2022, methodology): “Therefore, semi-supervised semantic segmentation [56] has been proposed and is attracting increasing attention.”
Semi-supervised Segmentation Based on Error-Correcting Supervision (2020, background): “Souly et al. [30] transferred this approach to semi-supervised segmentation, by keeping a generator that produces artiﬁcial samples but choosing a segmentation architecture for the discriminator.”
A Review on Generative Adversarial Networks: Algorithms, Theory, and Applications (2020, methodology): “GANs have been utilized in other image processing and computer vision tasks [354]–[357] such as object transfiguration [358], [359], semantic segmentation [360], visual saliency prediction [361], object tracking [362], [363], image dehazing [364]–[366], natural image matting [367], image inpainting ”