Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation

• URL: http://arxiv.org/abs/2206.09683v1
• Date: Mon, 20 Jun 2022 09:52:49 GMT
• Title: Distribution Regularized Self-Supervised Learning for Domain Adaptation of Semantic Segmentation
• Authors: Javed Iqbal, Hamza Rawal, Rehan Hafiz, Yu-Tseh Chi, Mohsen Ali
• Abstract summary: This paper proposes a pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to greedily learn the representations that capture inter-class variations. We capture pixel-level intra-class variations through class-aware multi-modal distribution learning.
• Score: 3.284878354988896
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: This paper proposes a novel pixel-level distribution regularization scheme (DRSL) for self-supervised domain adaptation of semantic segmentation. In a typical setting, the classification loss forces the semantic segmentation model to greedily learn the representations that capture inter-class variations in order to determine the decision (class) boundary. Due to the domain shift, this decision boundary is unaligned in the target domain, resulting in noisy pseudo labels adversely affecting self-supervised domain adaptation. To overcome this limitation, along with capturing inter-class variation, we capture pixel-level intra-class variations through class-aware multi-modal distribution learning (MMDL). Thus, the information necessary for capturing the intra-class variations is explicitly disentangled from the information necessary for inter-class discrimination. Features captured thus are much more informative, resulting in pseudo-labels with low noise. This disentanglement allows us to perform separate alignments in discriminative space and multi-modal distribution space, using cross-entropy based self-learning for the former. For later, we propose a novel stochastic mode alignment method, by explicitly decreasing the distance between the target and source pixels that map to the same mode. The distance metric learning loss, computed over pseudo-labels and backpropagated from multi-modal modeling head, acts as the regularizer over the base network shared with the segmentation head. The results from comprehensive experiments on synthetic to real domain adaptation setups, i.e., GTA-V/SYNTHIA to Cityscapes, show that DRSL outperforms many existing approaches (a minimum margin of 2.3% and 2.5% in mIoU for SYNTHIA to Cityscapes).

Related papers

• Active Domain Adaptation with Multi-level Contrastive Units for Semantic Segmentation [22.048328293739182]
  We propose a novel Active Domain Adaptation scheme with Multi-level Contrastive Units (ADA-MCU) for semantic image segmentation. ADA-MCU is constructed from intra-image, cross-image, and cross-domain levels by using both labeled and unlabeled pixels. We show that the proposed method achieves competitive performance against state-of-the-art SSDA methods with 50% fewer labeled pixels and significantly outperforms state-of-the-art with a large margin by using the same level of annotation cost.
  arXiv  Detail & Related papers  (2022-05-23T10:55:39Z)
• Attention-based Cross-Layer Domain Alignment for Unsupervised Domain Adaptation [14.65316832227658]
  Unsupervised domain adaptation (UDA) aims to learn transferable knowledge from a labeled source domain and adapts a trained model to an unlabeled target domain. One prevailing strategy is to minimize the distribution discrepancy by aligning their semantic features extracted by deep models.
  arXiv  Detail & Related papers  (2022-02-27T08:36:12Z)
• Semi-supervised Domain Adaptive Structure Learning [72.01544419893628]
  Semi-supervised domain adaptation (SSDA) is a challenging problem requiring methods to overcome both 1) overfitting towards poorly annotated data and 2) distribution shift across domains. We introduce an adaptive structure learning method to regularize the cooperation of SSL and DA.
  arXiv  Detail & Related papers  (2021-12-12T06:11:16Z)
• Semi-supervised Domain Adaptation for Semantic Segmentation [3.946367634483361]
  We propose a novel two-step semi-supervised dual-domain adaptation (SSDDA) approach to address both cross- and intra-domain gaps in semantic segmentation. We demonstrate that the proposed approach outperforms state-of-the-art methods on two common synthetic-to-real semantic segmentation benchmarks.
  arXiv  Detail & Related papers  (2021-10-20T16:13:00Z)
• HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning [74.76431541169342]
  Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. We propose a novel hierarchical semantic-visual adaptation (HSVA) framework to align semantic and visual domains. Experiments on four benchmark datasets demonstrate HSVA achieves superior performance on both conventional and generalized ZSL.
  arXiv  Detail & Related papers  (2021-09-30T14:27:50Z)
• Margin Preserving Self-paced Contrastive Learning Towards Domain Adaptation for Medical Image Segmentation [51.93711960601973]
  We propose a novel margin preserving self-paced contrastive Learning model for cross-modal medical image segmentation. With the guidance of progressively refined semantic prototypes, a novel margin preserving contrastive loss is proposed to boost the discriminability of embedded representation space. Experiments on cross-modal cardiac segmentation tasks demonstrate that MPSCL significantly improves semantic segmentation performance.
  arXiv  Detail & Related papers  (2021-03-15T15:23:10Z)
• Cross-Domain Grouping and Alignment for Domain Adaptive Semantic Segmentation [74.3349233035632]
  Existing techniques to adapt semantic segmentation networks across the source and target domains within deep convolutional neural networks (CNNs) do not consider an inter-class variation within the target domain itself or estimated category. We introduce a learnable clustering module, and a novel domain adaptation framework called cross-domain grouping and alignment. Our method consistently boosts the adaptation performance in semantic segmentation, outperforming the state-of-the-arts on various domain adaptation settings.
  arXiv  Detail & Related papers  (2020-12-15T11:36:21Z)
• Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation [55.73722120043086]
  We develop a "Select, Label, and Mix" (SLM) framework to learn discriminative invariant feature representations for partial domain adaptation. First, we present a simple yet efficient "select" module that automatically filters out outlier source samples to avoid negative transfer. Second, the "label" module iteratively trains the classifier using both the labeled source domain data and the generated pseudo-labels for the target domain to enhance the discriminability of the latent space.
  arXiv  Detail & Related papers  (2020-12-06T19:29:32Z)
• Learning from Scale-Invariant Examples for Domain Adaptation in Semantic Segmentation [6.320141734801679]
  We propose a novel approach of exploiting scale-invariance property of semantic segmentation model for self-supervised domain adaptation. Our algorithm is based on a reasonable assumption that, in general, regardless of the size of the object and stuff (given context) the semantic labeling should be unchanged. We show that this constraint is violated over the images of the target domain, and hence could be used to transfer labels in-between differently scaled patches.
  arXiv  Detail & Related papers  (2020-07-28T19:40:45Z)
• Alleviating Semantic-level Shift: A Semi-supervised Domain Adaptation Method for Semantic Segmentation [97.8552697905657]
  A key challenge of this task is how to alleviate the data distribution discrepancy between the source and target domains. We propose Alleviating Semantic-level Shift (ASS), which can successfully promote the distribution consistency from both global and local views. We apply our ASS to two domain adaptation tasks, from GTA5 to Cityscapes and from Synthia to Cityscapes.
  arXiv  Detail & Related papers  (2020-04-02T03:25:05Z)

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.