Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation

• URL: http://arxiv.org/abs/2206.11180v1
• Date: Wed, 22 Jun 2022 15:40:52 GMT
• Title: Optimal transport meets noisy label robust loss and MixUp regularization for domain adaptation
• Authors: Kilian Fatras, Hiroki Naganuma, Ioannis Mitliagkas
• Abstract summary: Deep neural networks trained on a source training set perform poorly on target images which do not belong to the training domain. One strategy to improve these performances is to align the source and target image distributions in an embedded space using optimal transport (OT) We propose to couple the MixUp regularization citepzhang 2018mixup with a loss that is robust to noisy labels in order to improve domain adaptation performance.
• Score: 13.080485957000462
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: It is common in computer vision to be confronted with domain shift: images which have the same class but different acquisition conditions. In domain adaptation (DA), one wants to classify unlabeled target images using source labeled images. Unfortunately, deep neural networks trained on a source training set perform poorly on target images which do not belong to the training domain. One strategy to improve these performances is to align the source and target image distributions in an embedded space using optimal transport (OT). However OT can cause negative transfer, i.e. aligning samples with different labels, which leads to overfitting especially in the presence of label shift between domains. In this work, we mitigate negative alignment by explaining it as a noisy label assignment to target images. We then mitigate its effect by appropriate regularization. We propose to couple the MixUp regularization \citep{zhang2018mixup} with a loss that is robust to noisy labels in order to improve domain adaptation performance. We show in an extensive ablation study that a combination of the two techniques is critical to achieve improved performance. Finally, we evaluate our method, called \textsc{mixunbot}, on several benchmarks and real-world DA problems.

Related papers

• Local-Global Pseudo-label Correction for Source-free Domain Adaptive Medical Image Segmentation [5.466962214217334]
  Domain shift is a commonly encountered issue in medical imaging solutions. Concerns regarding patient privacy and potential degradation of image quality have led to an increased focus on source-free domain adaptation. We propose a novel approach called the local-global pseudo-label correction (LGDA) method for source-free domain adaptive medical image segmentation.
  arXiv  Detail & Related papers  (2023-08-28T05:29:59Z)
• I2F: A Unified Image-to-Feature Approach for Domain Adaptive Semantic Segmentation [55.633859439375044]
  Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. Key idea to tackle this problem is to perform both image-level and feature-level adaptation jointly. This paper proposes a novel UDA pipeline for semantic segmentation that unifies image-level and feature-level adaptation.
  arXiv  Detail & Related papers  (2023-01-03T15:19:48Z)
• Semi-supervised domain adaptation with CycleGAN guided by a downstream task loss [4.941630596191806]
  Domain adaptation is of huge interest as labeling is an expensive and error-prone task. Image-to-image approaches can be used to mitigate the shift in the input. We propose a "task aware" version of a GAN in an image-to-image domain adaptation approach.
  arXiv  Detail & Related papers  (2022-08-18T13:13:30Z)
• Target and Task specific Source-Free Domain Adaptive Image Segmentation [73.78898054277538]
  We propose a two-stage approach for source-free domain adaptive image segmentation. We focus on generating target-specific pseudo labels while suppressing high entropy regions. In the second stage, we focus on adapting the network for task-specific representation.
  arXiv  Detail & Related papers  (2022-03-29T17:50:22Z)
• Global and Local Alignment Networks for Unpaired Image-to-Image Translation [170.08142745705575]
  The goal of unpaired image-to-image translation is to produce an output image reflecting the target domain's style. Due to the lack of attention to the content change in existing methods, semantic information from source images suffers from degradation during translation. We introduce a novel approach, Global and Local Alignment Networks (GLA-Net) Our method effectively generates sharper and more realistic images than existing approaches.
  arXiv  Detail & Related papers  (2021-11-19T18:01:54Z)
• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation [97.74059510314554]
  Unsupervised domain adaptation (UDA) for semantic segmentation aims to adapt a segmentation model trained on the labeled source domain to the unlabeled target domain. Existing methods try to learn domain invariant features while suffering from large domain gaps. We propose a novel Dual Soft-Paste (DSP) method in this paper.
  arXiv  Detail & Related papers  (2021-07-20T16:22:40Z)
• 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)
• Semi-Supervised Domain Adaptation with Prototypical Alignment and Consistency Learning [86.6929930921905]
  This paper studies how much it can help address domain shifts if we further have a few target samples labeled. To explore the full potential of landmarks, we incorporate a prototypical alignment (PA) module which calculates a target prototype for each class from the landmarks. Specifically, we severely perturb the labeled images, making PA non-trivial to achieve and thus promoting model generalizability.
  arXiv  Detail & Related papers  (2021-04-19T08:46:08Z)

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.