Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network

Souly, Nasim; Spampinato, Concetto; Shah, Mubarak

doi:10.48550/arxiv.1703.09695

Cited by 14 publications

(19 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After every iteration, the selected candidate labels and the segmentation network outputs both improve together. Generative adversarial networks have proven to be effective in this filed starting from [32], where the discriminator network is modified to accomplish the task of semantic segmentation. The discriminator assigns to every pixel of the input image either a label of one of the semantic classes or a fake label.…”

Section: Weakly-and Semi-supervised Learningmentioning

confidence: 99%

Unsupervised Domain Adaptation in Semantic Segmentation: a Review

Toldo¹,

Maracani²,

Michieli³

et al. 2020

Preprint

View full text Add to dashboard Cite

The aim of this paper is to give an overview of the recent advancements in the Unsupervised Domain Adaptation (UDA) of deep networks for semantic segmentation. This task is attracting a wide interest, since semantic segmentation models require a huge amount of labeled data and the lack of data fitting specific requirements is the main limitation in the deployment of these techniques. This problem has been recently explored and has rapidly grown with a large number of ad-hoc approaches. This motivates us to build a comprehensive overview of the proposed methodologies and to provide a clear categorization. In this paper, we start by introducing the problem, its formulation and the various scenarios that can be considered. Then, we introduce the different levels at which adaptation strategies may be applied: namely, at the input (image) level, at the internal features representation and at the output level. Furthermore, we present a detailed overview of the literature in the field, dividing previous methods based on the following (non mutually exclusive) categories: adversarial learning, generative-based, analysis of the classifier discrepancies, self-teaching, entropy minimization, curriculum learning and multi-task learning. Novel research directions are also briefly introduced to give a hint of interesting open problems in the field. Finally, a comparison of the performance of the various methods in the widely used autonomous driving scenario is presented.

show abstract

Section: Weakly-and Semi-supervised Learningmentioning

confidence: 99%

Unsupervised Domain Adaptation in Semantic Segmentation: a Review

Toldo¹,

Maracani²,

Michieli³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The first family of approaches we consider is semisupervised methods. They can be divided into methods exploiting weakly annotated data (e.g., with only image-wise labels or only bounding boxes) [20]- [27] or methods for which only part of the data is labeled while the other is completely unlabeled [5], [6], [21], [28], [29]. The work of [30] has opened the way to adversarial learning approaches for the semantic segmentation task while [21] to their application to semi-supervised learning.…”

Section: Related Workmentioning

confidence: 99%

“…They can be divided into methods exploiting weakly annotated data (e.g., with only image-wise labels or only bounding boxes) [20]- [27] or methods for which only part of the data is labeled while the other is completely unlabeled [5], [6], [21], [28], [29]. The work of [30] has opened the way to adversarial learning approaches for the semantic segmentation task while [21] to their application to semi-supervised learning. The approaches of [5], [6] are also based on adversarial learning but exploit a Fully Convolutional Discriminator (FCD) trying to discriminate between the predicted probability maps and the ground truth segmentation distributions at pixel-level.…”

Section: Related Workmentioning

confidence: 99%

Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

Michieli

Biasetton

Agresti

et al. 2020

IEEE Trans. Intell. Veh.

View full text Add to dashboard Cite

Deep learning techniques have been widely used in autonomous driving systems for the semantic understanding of urban scenes, however they need a huge amount of labeled data for training, which is difficult and expensive to acquire. A recently proposed workaround is to train deep networks using synthetic data, however the domain shift between real world and synthetic representations limits the performance. In this work a novel unsupervised domain adaptation strategy is introduced to solve this issue. The proposed learning strategy is driven by three components: a standard supervised learning loss on labeled synthetic data, an adversarial learning module that exploits both labeled synthetic data and unlabeled real data and finally a selfteaching strategy exploiting unlabeled data. The last component exploits a region growing framework guided by the segmentation confidence. Furthermore, we weighted this component on the basis of the class frequencies to enhance the performance on less common classes. Experimental results prove the effectiveness of the proposed strategy in adapting a segmentation network trained on synthetic datasets, like GTA5 and SYNTHIA, to real world datasets like Cityscapes and Mapillary.

show abstract

“…To the best of our knowledge, there is no previous work to learning human semantic parsing with image-level supervision but only weakly-supervised methods for semantic segmentation [16,47,19,12,11,33,44,62], which aim to locate objects like person, horse or dog at pixel-level with image-level supervision. However, all these methods cannot be used for the weakly-supervised human parsing task because they focus on different levels.…”

Section: Semantic Learning With Image-level Supervisionmentioning

confidence: 99%

Identity-Guided Human Semantic Parsing for Person Re-Identification

Zhu

Guo

Liu

et al. 2020

Preprint

View full text Add to dashboard Cite

Existing alignment-based methods have to employ the pretrained human parsing models to achieve the pixel-level alignment, and cannot identify the personal belongings (e.g., backpacks and reticule) which are crucial to person re-ID. In this paper, we propose the identityguided human semantic parsing approach (ISP) to locate both the human body parts and personal belongings at pixel-level for aligned person re-ID only with person identity labels. We design the cascaded clustering on feature maps to generate the pseudo-labels of human parts. Specifically, for the pixels of all images of a person, we first group them to foreground or background and then group the foreground pixels to human parts. The cluster assignments are subsequently used as pseudo-labels of human parts to supervise the part estimation and ISP iteratively learns the feature maps and groups them. Finally, local features of both human body parts and personal belongings are obtained according to the selflearned part estimation, and only features of visible parts are utilized for the retrieval. Extensive experiments on three widely used datasets validate the superiority of ISP over lots of state-of-the-art methods. Our code is available at https://github.com/CASIA-IVA-Lab/ISP-reID.

show abstract

Semi and Weakly Supervised Semantic Segmentation Using Generative Adversarial Network

Cited by 14 publications

References 0 publications

Unsupervised Domain Adaptation in Semantic Segmentation: a Review

Unsupervised Domain Adaptation in Semantic Segmentation: a Review

Adversarial Learning and Self-Teaching Techniques for Domain Adaptation in Semantic Segmentation

Identity-Guided Human Semantic Parsing for Person Re-Identification

Contact Info

Product

Resources

About