Unsupervised Domain Adaptation with Contrastive Learning for OCT Segmentation

Gomariz, Álvaro; Lu, Huanxiang; Li, Yun Yvonna; Albrecht, Thomas; Maunz, Andreas; Benmansour, Fethallah; Valcarcel, Alessandra M.; Luu, Jennifer; Ferrara, Daniela; Göksel, Orçun

doi:10.1007/978-3-031-16452-1_34

Cited by 6 publications

(1 citation statement)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liu et al [17] proposed a margin-preserving constraint along with a self-paced CL framework, gradually increasing the training data difficulty. Gomariz et al [8] proposed a CL framework with an unconventional channel-wise aggregated projection head for inter-slice representation learning. However, traditional CL utilized for DA on images with entangled style and content leads to mixed representation learning, whereas ideally, it should learn discriminative content features invariant to style representation.…”

Section: Introductionmentioning

confidence: 99%

Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation

Basak,

Yin

2023

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

View full text Add to dashboard Cite

Although unsupervised domain adaptation (UDA) is a promising direction to alleviate domain shift, they fall short of their supervised counterparts. In this work, we investigate relatively less explored semisupervised domain adaptation (SSDA) for medical image segmentation, where access to a few labeled target samples can improve the adaptation performance substantially. Specifically, we propose a two-stage training process. First, an encoder is pre-trained in a self-learning paradigm using a novel domain-content disentangled contrastive learning (CL) along with a pixel-level feature consistency constraint. The proposed CL enforces the encoder to learn discriminative content-specific but domaininvariant semantics on a global scale from the source and target images, whereas consistency regularization enforces the mining of local pixel-level information by maintaining spatial sensitivity. This pre-trained encoder, along with a decoder, is further fine-tuned for the downstream task, (i.e. pixel-level segmentation) using a semi-supervised setting. Furthermore, we experimentally validate that our proposed method can easily be extended for UDA settings, adding to the superiority of the proposed strategy. Upon evaluation on two domain adaptive image segmentation tasks, our proposed method outperforms the SoTA methods, both in SSDA and UDA settings. Code is available at GitHub.

show abstract

Section: Introductionmentioning

confidence: 99%