# Weakly-Supervised Cross-Domain Adaptation for Endoscopic Lesions Segmentation

arXiv: https://arxiv.org/abs/2012.04170 · HTML: https://mlsanity.com/paper/2012.04170/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Dec 2020.

## Built on by (most cited first, 6 of 6)

- [Learning Bounds for Open-Set Learning](https://mlsanity.com/paper/2106.15792/) (2021)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Prototype Correlation Matching and Class-Relation Reasoning for Few-Shot Medical Image Segmentation](https://mlsanity.com/paper/2406.05054/) (2024)
- [Cross-Site Severity Assessment of COVID-19 from CT Images via Domain Adaptation](https://mlsanity.com/paper/2109.03478/) (2021)
- [Rethinking Polyp Segmentation from an Out-of-Distribution Perspective](https://mlsanity.com/paper/2306.07792/) (2023)
- [A Class-wise Non-salient Region Generalized Framework for Video Semantic Segmentation](https://mlsanity.com/paper/2212.14154/) (2022)

## Abstract (arXiv)

Weakly-supervised learning has attracted growing research attention on medical lesions segmentation due to significant saving in pixel-level annotation cost. However, 1) most existing methods require effective prior and constraints to explore the intrinsic lesions characterization, which only generates incorrect and rough prediction; 2) they neglect the underlying semantic dependencies among weakly-labeled target enteroscopy diseases and fully-annotated source gastroscope lesions, while forcefully utilizing untransferable dependencies leads to the negative performance. To tackle above issues, we propose a new weakly-supervised lesions transfer framework, which can not only explore transferable domain-invariant knowledge across different datasets, but also prevent the negative transfer of untransferable representations. Specifically, a Wasserstein quantified transferability framework is developed to highlight widerange transferable contextual dependencies, while neglecting the irrelevant semantic characterizations. Moreover, a novel selfsupervised pseudo label generator is designed to equally provide confident pseudo pixel labels for both hard-to-transfer and easyto-transfer target samples. It inhibits the enormous deviation of false pseudo pixel labels under the self-supervision manner. Afterwards, dynamically-searched feature centroids are aligned to narrow category-wise distribution shift. Comprehensive theoretical analysis and experiments show the superiority of our model on the endoscopic dataset and several public datasets.