Semantic Image Segmentation: Two Decades of Research

• URL: http://arxiv.org/abs/2302.06378v1
• Date: Mon, 13 Feb 2023 14:11:05 GMT
• Title: Semantic Image Segmentation: Two Decades of Research
• Authors: Gabriela Csurka, Riccardo Volpi and Boris Chidlovskii
• Abstract summary: This book is an effort to summarize two decades of research in the field of semantic image segmentation (SiS) We propose a review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We unveil newer trends such as multi-domain learning, domain generalization, domain incremental learning, test-time adaptation and source-free domain adaptation.
• Score: 22.533249554532322
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Semantic image segmentation (SiS) plays a fundamental role in a broad variety of computer vision applications, providing key information for the global understanding of an image. This survey is an effort to summarize two decades of research in the field of SiS, where we propose a literature review of solutions starting from early historical methods followed by an overview of more recent deep learning methods including the latest trend of using transformers. We complement the review by discussing particular cases of the weak supervision and side machine learning techniques that can be used to improve the semantic segmentation such as curriculum, incremental or self-supervised learning. State-of-the-art SiS models rely on a large amount of annotated samples, which are more expensive to obtain than labels for tasks such as image classification. Since unlabeled data is instead significantly cheaper to obtain, it is not surprising that Unsupervised Domain Adaptation (UDA) reached a broad success within the semantic segmentation community. Therefore, a second core contribution of this book is to summarize five years of a rapidly growing field, Domain Adaptation for Semantic Image Segmentation (DASiS) which embraces the importance of semantic segmentation itself and a critical need of adapting segmentation models to new environments. In addition to providing a comprehensive survey on DASiS techniques, we unveil also newer trends such as multi-domain learning, domain generalization, domain incremental learning, test-time adaptation and source-free domain adaptation. Finally, we conclude this survey by describing datasets and benchmarks most widely used in SiS and DASiS and briefly discuss related tasks such as instance and panoptic image segmentation, as well as applications such as medical image segmentation.

Related papers

• Image Segmentation in Foundation Model Era: A Survey [99.19456390358211]
  Current research in image segmentation lacks a detailed analysis of distinct characteristics, challenges, and solutions associated with these advancements. This survey seeks to fill this gap by providing a thorough review of cutting-edge research centered around FM-driven image segmentation. An exhaustive overview of over 300 segmentation approaches is provided to encapsulate the breadth of current research efforts.
  arXiv  Detail & Related papers  (2024-08-23T10:07:59Z)
• Grounding Stylistic Domain Generalization with Quantitative Domain Shift Measures and Synthetic Scene Images [63.58800688320182]
  Domain Generalization is a challenging task in machine learning. Current methodology lacks quantitative understanding about shifts in stylistic domain. We introduce a new DG paradigm to address these risks.
  arXiv  Detail & Related papers  (2024-05-24T22:13:31Z)
• Semi-Supervised Semantic Segmentation Based on Pseudo-Labels: A Survey [49.47197748663787]
  This review aims to provide a first comprehensive and organized overview of the state-of-the-art research results on pseudo-label methods in the field of semi-supervised semantic segmentation. In addition, we explore the application of pseudo-label technology in medical and remote-sensing image segmentation.
  arXiv  Detail & Related papers  (2024-03-04T10:18:38Z)
• Weakly-Supervised Semantic Segmentation with Image-Level Labels: from Traditional Models to Foundation Models [33.690846523358836]
  Weakly-supervised semantic segmentation (WSSS) is an effective solution to avoid pixel-level labels. We focus on the WSSS with image-level labels, which is the most challenging form of WSSS. We investigate the applicability of visual foundation models, such as the Segment Anything Model (SAM), in the context of WSSS.
  arXiv  Detail & Related papers  (2023-10-19T07:16:54Z)
• Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey [24.622211579286127]
  This survey is an effort to summarize five years of this incredibly rapidly growing field. We present the most important semantic segmentation methods. We unveil newer trends such as multi-domain learning, domain generalization, test-time adaptation or source-free domain adaptation.
  arXiv  Detail & Related papers  (2021-12-06T18:47:41Z)
• Novel Class Discovery in Semantic Segmentation [104.30729847367104]
  We introduce a new setting of Novel Class Discovery in Semantic (NCDSS) It aims at segmenting unlabeled images containing new classes given prior knowledge from a labeled set of disjoint classes. In NCDSS, we need to distinguish the objects and background, and to handle the existence of multiple classes within an image. We propose the Entropy-based Uncertainty Modeling and Self-training (EUMS) framework to overcome noisy pseudo-labels.
  arXiv  Detail & Related papers  (2021-12-03T13:31:59Z)
• Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation [94.16816278191477]
  We present a framework for semi-adaptive and domain-supervised semantic segmentation. It is enhanced by self-supervised monocular depth estimation trained only on unlabeled image sequences. We validate the proposed model on the Cityscapes dataset.
  arXiv  Detail & Related papers  (2021-08-28T01:33:38Z)
• A Few Guidelines for Incremental Few-Shot Segmentation [57.34237650765928]
  Given a pretrained segmentation model and few images containing novel classes, our goal is to learn to segment novel classes while retaining the ability to segment previously seen ones. We show how the main problems of end-to-end training in this scenario are. i) the drift of the batch-normalization statistics toward novel classes that we can fix with batch renormalization and. ii) the forgetting of old classes, that we can fix with regularization strategies.
  arXiv  Detail & Related papers  (2020-11-30T20:45:56Z)
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review [22.366638308792734]
  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.
  arXiv  Detail & Related papers  (2020-05-21T20:10:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.