Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations

• URL: http://arxiv.org/abs/2401.01035v1
• Date: Tue, 2 Jan 2024 04:48:49 GMT
• Title: Online Continual Domain Adaptation for Semantic Image Segmentation Using Internal Representations
• Authors: Serban Stan, Mohammad Rostami
• Abstract summary: We develop an online UDA algorithm for semantic segmentation of images that improves model generalization on unannotated domains. We evaluate our approach on well established semantic segmentation datasets and demonstrate it compares favorably against state-of-the-art (SOTA) semantic segmentation methods.
• Score: 28.549418215123936
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Semantic segmentation models trained on annotated data fail to generalize well when the input data distribution changes over extended time period, leading to requiring re-training to maintain performance. Classic Unsupervised domain adaptation (UDA) attempts to address a similar problem when there is target domain with no annotated data points through transferring knowledge from a source domain with annotated data. We develop an online UDA algorithm for semantic segmentation of images that improves model generalization on unannotated domains in scenarios where source data access is restricted during adaptation. We perform model adaptation is by minimizing the distributional distance between the source latent features and the target features in a shared embedding space. Our solution promotes a shared domain-agnostic latent feature space between the two domains, which allows for classifier generalization on the target dataset. To alleviate the need of access to source samples during adaptation, we approximate the source latent feature distribution via an appropriate surrogate distribution, in this case a Gassian mixture model (GMM). We evaluate our approach on well established semantic segmentation datasets and demonstrate it compares favorably against state-of-the-art (SOTA) UDA semantic segmentation methods.

Related papers

• Open-Set Domain Adaptation with Visual-Language Foundation Models [51.49854335102149]
  Unsupervised domain adaptation (UDA) has proven to be very effective in transferring knowledge from a source domain to a target domain with unlabeled data. Open-set domain adaptation (ODA) has emerged as a potential solution to identify these classes during the training phase.
  arXiv  Detail & Related papers  (2023-07-30T11:38:46Z)
• Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning [122.62311703151215]
  Divide and Contrast (DaC) aims to connect the good ends of both worlds while bypassing their limitations. DaC divides the target data into source-like and target-specific samples, where either group of samples is treated with tailored goals. We further align the source-like domain with the target-specific samples using a memory bank-based Maximum Mean Discrepancy (MMD) loss to reduce the distribution mismatch.
  arXiv  Detail & Related papers  (2022-11-12T09:21:49Z)
• Source-Free Domain Adaptation via Distribution Estimation [106.48277721860036]
  Domain Adaptation aims to transfer the knowledge learned from a labeled source domain to an unlabeled target domain whose data distributions are different. Recently, Source-Free Domain Adaptation (SFDA) has drawn much attention, which tries to tackle domain adaptation problem without using source data. In this work, we propose a novel framework called SFDA-DE to address SFDA task via source Distribution Estimation.
  arXiv  Detail & Related papers  (2022-04-24T12:22:19Z)
• Adapting Off-the-Shelf Source Segmenter for Target Medical Image Segmentation [12.703234995718372]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled and unseen target domain. Access to the source domain data at the adaptation stage is often limited, due to data storage or privacy issues. We propose to adapt an off-the-shelf" segmentation model pre-trained in the source domain to the target domain.
  arXiv  Detail & Related papers  (2021-06-23T16:16:55Z)
• Gradual Domain Adaptation via Self-Training of Auxiliary Models [50.63206102072175]
  Domain adaptation becomes more challenging with increasing gaps between source and target domains. We propose self-training of auxiliary models (AuxSelfTrain) that learns models for intermediate domains. Experiments on benchmark datasets of unsupervised and semi-supervised domain adaptation verify its efficacy.
  arXiv  Detail & Related papers  (2021-06-18T03:15:25Z)
• Instance Level Affinity-Based Transfer for Unsupervised Domain Adaptation [74.71931918541748]
  We propose an instance affinity based criterion for source to target transfer during adaptation, called ILA-DA. We first propose a reliable and efficient method to extract similar and dissimilar samples across source and target, and utilize a multi-sample contrastive loss to drive the domain alignment process. We verify the effectiveness of ILA-DA by observing consistent improvements in accuracy over popular domain adaptation approaches on a variety of benchmark datasets.
  arXiv  Detail & Related papers  (2021-04-03T01:33:14Z)
• Source-Free Domain Adaptation for Semantic Segmentation [11.722728148523366]
  Unsupervised Domain Adaptation (UDA) can tackle the challenge that convolutional neural network-based approaches for semantic segmentation heavily rely on the pixel-level annotated data. We propose a source-free domain adaptation framework for semantic segmentation, namely SFDA, in which only a well-trained source model and an unlabeled target domain dataset are available for adaptation.
  arXiv  Detail & Related papers  (2021-03-30T14:14:29Z)
• Unsupervised BatchNorm Adaptation (UBNA): A Domain Adaptation Method for Semantic Segmentation Without Using Source Domain Representations [35.586031601299034]
  Unsupervised BatchNorm Adaptation (UBNA) adapts a given pre-trained model to an unseen target domain. We partially adapt the normalization layer statistics to the target domain using an exponentially decaying momentum factor. Compared to standard UDA approaches we report a trade-off between performance and usage of source domain representations.
  arXiv  Detail & Related papers  (2020-11-17T08:37:40Z)
• Unsupervised Model Adaptation for Continual Semantic Segmentation [15.820660013260584]
  We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. We provide theoretical analysis and explain conditions under which our algorithm is effective. Experiments on benchmark adaptation task demonstrate our method achieves competitive performance even compared with joint UDA approaches.
  arXiv  Detail & Related papers  (2020-09-26T04:55:50Z)
• Sequential Model Adaptation Using Domain Agnostic Internal Distributions [31.3178953771424]
  We develop an algorithm for sequential adaptation of a classifier that is trained for a source domain to generalize in an unannotated target domain. We consider that the model has been trained on the source domain annotated data and then it needs to be adapted using the target domain unannotated data when the source domain data is not accessible.
  arXiv  Detail & Related papers  (2020-07-01T03:14:17Z)
• Do We Really Need to Access the Source Data? Source Hypothesis Transfer for Unsupervised Domain Adaptation [102.67010690592011]
  Unsupervised adaptationUDA (UDA) aims to leverage the knowledge learned from a labeled source dataset to solve similar tasks in a new unlabeled domain. Prior UDA methods typically require to access the source data when learning to adapt the model. This work tackles a practical setting where only a trained source model is available and how we can effectively utilize such a model without source data to solve UDA problems.
  arXiv  Detail & Related papers  (2020-02-20T03:13:58Z)

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.