Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

• URL: http://arxiv.org/abs/2309.16127v1
• Date: Thu, 28 Sep 2023 03:15:47 GMT
• Title: Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation
• Authors: Tingliang Feng, Hao Shi, Xueyang Liu, Wei Feng, Liang Wan, Yanlin Zhou and Di Lin
• Abstract summary: This paper proposes the Object Style Compensation, where we construct the Object-Level Discrepancy Memory. We learn the discrepancy features from the images of source and target domains, storing the discrepancy features in memory. Our method enables a more accurate computation of the pseudo annotations for target domain's images, thus yielding state-of-the-art results on different datasets.
• Score: 23.925791263194622
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Many methods of semantic image segmentation have borrowed the success of open compound domain adaptation. They minimize the style gap between the images of source and target domains, more easily predicting the accurate pseudo annotations for target domain's images that train segmentation network. The existing methods globally adapt the scene style of the images, whereas the object styles of different categories or instances are adapted improperly. This paper proposes the Object Style Compensation, where we construct the Object-Level Discrepancy Memory with multiple sets of discrepancy features. The discrepancy features in a set capture the style changes of the same category's object instances adapted from target to source domains. We learn the discrepancy features from the images of source and target domains, storing the discrepancy features in memory. With this memory, we select appropriate discrepancy features for compensating the style information of the object instances of various categories, adapting the object styles to a unified style of source domain. Our method enables a more accurate computation of the pseudo annotations for target domain's images, thus yielding state-of-the-art results on different datasets.

Related papers

• Domain-invariant Prototypes for Semantic Segmentation [30.932130453313537]
  We present an easy-to-train framework that learns domain-invariant prototypes for domain adaptive semantic segmentation. Our method involves only one-stage training and does not need to be trained on large-scale un-annotated target images.
  arXiv  Detail & Related papers  (2022-08-12T02:21:05Z)
• Bi-directional Contrastive Learning for Domain Adaptive Semantic Segmentation [29.573404843110836]
  A key to domain adaptive semantic segmentation is to learn domain-invariant and discriminative features without target ground-truth labels. We propose a bi-directional pixel-prototype contrastive learning framework that minimizes intra-class variations of features for the same object class.
  arXiv  Detail & Related papers  (2022-07-22T05:57:54Z)
• Panoptic-based Object Style-Align for Image-to-Image Translation [2.226472061870956]
  We propose panoptic-based object style-align generative adversarial networks (POSA-GANs) for image-to-image translation. The proposed method was systematically compared with different competing methods and obtained significant improvement on both image quality and object recognition performance for translated images.
  arXiv  Detail & Related papers  (2021-12-03T14:28:11Z)
• Disentangled Unsupervised Image Translation via Restricted Information Flow [61.44666983942965]
  Many state-of-art methods hard-code the desired shared-vs-specific split into their architecture. We propose a new method that does not rely on inductive architectural biases. We show that the proposed method achieves consistently high manipulation accuracy across two synthetic and one natural dataset.
  arXiv  Detail & Related papers  (2021-11-26T00:27:54Z)
• Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation [50.621269117524925]
  Domain adaptive semantic segmentation refers to making predictions on a certain target domain with only annotations of a specific source domain. We present a semantic distribution-aware contrastive adaptation algorithm that enables pixel-wise representation alignment. We evaluate SDCA on multiple benchmarks, achieving considerable improvements over existing algorithms.
  arXiv  Detail & Related papers  (2021-05-11T13:21:25Z)
• Memory-guided Unsupervised Image-to-image Translation [54.1903150849536]
  We present an unsupervised framework for instance-level image-to-image translation. We show that our model outperforms recent instance-level methods.
  arXiv  Detail & Related papers  (2021-04-12T03:02:51Z)
• DRANet: Disentangling Representation and Adaptation Networks for Unsupervised Cross-Domain Adaptation [23.588766224169493]
  DRANet is a network architecture that disentangles image representations and transfers the visual attributes in a latent space for unsupervised cross-domain adaptation. Our model encodes individual representations of content (scene structure) and style (artistic appearance) from both source and target images. It adapts the domain by incorporating the transferred style factor into the content factor along with learnable weights specified for each domain.
  arXiv  Detail & Related papers  (2021-03-24T18:54:23Z)
• Affinity Space Adaptation for Semantic Segmentation Across Domains [57.31113934195595]
  In this paper, we address the problem of unsupervised domain adaptation (UDA) in semantic segmentation. Motivated by the fact that source and target domain have invariant semantic structures, we propose to exploit such invariance across domains. We develop two affinity space adaptation strategies: affinity space cleaning and adversarial affinity space alignment.
  arXiv  Detail & Related papers  (2020-09-26T10:28:11Z)
• TriGAN: Image-to-Image Translation for Multi-Source Domain Adaptation [82.52514546441247]
  We propose the first approach for Multi-Source Domain Adaptation (MSDA) based on Generative Adversarial Networks. Our method is inspired by the observation that the appearance of a given image depends on three factors: the domain, the style and the content. We test our approach using common MSDA benchmarks, showing that it outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-04-19T05:07:22Z)
• Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation [105.96860932833759]
  State-of-the-art approaches prove that performing semantic-level alignment is helpful in tackling the domain shift issue. We propose to improve the semantic-level alignment with different strategies for stuff regions and for things. In addition to our proposed method, we show that our method can help ease this issue by minimizing the most similar stuff and instance features between the source and the target domains.
  arXiv  Detail & Related papers  (2020-03-18T04:43:25Z)

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.