Unsupervised Cross-domain Pulmonary Nodule Detection without Source Data

by   Rui Xu, et al.
Wuhan University

Cross domain pulmonary nodule detection suffers from performance degradation due to large shift of data distributions between the source and target domain. Besides, considering the high cost of medical data annotation, it is often assumed that the target images are unlabeled. Existing approaches have made much progress for this unsupervised domain adaptation setting. However, this setting is still rarely plausible in the medical application since the source medical data are often not accessible due to the privacy concerns. This motivates us to propose a Source-free Unsupervised cross-domain method for Pulmonary nodule detection (SUP). It first adapts the source model to the target domain by utilizing instance-level contrastive learning. Then the adapted model is trained in a teacher-student interaction manner, and a weighted entropy loss is incorporated to further improve the accuracy. Extensive experiments by adapting a pre-trained source model to three popular pulmonary nodule datasets demonstrate the effectiveness of our method.


page 1

page 4

page 5

page 6

page 8


Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection

Unsupervised Domain Adaptation (UDA) technique has been explored in 3D c...

TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition

Gait, i.e., the movement pattern of human limbs during locomotion, is a ...

Instance Relation Graph Guided Source-Free Domain Adaptive Object Detection

Unsupervised Domain Adaptation (UDA) is an effective approach to tackle ...

MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech Recognition

End-to-end automatic speech recognition (ASR) usually suffers from perfo...

Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency

Deep learning-based 3D object detection has achieved unprecedented succe...

Burn After Reading: Online Adaptation for Cross-domain Streaming Data

In the context of online privacy, many methods propose complex privacy a...

Unsupervised Cross-Domain Recognition by Identifying Compact Joint Subspaces

This paper introduces a new method to solve the cross-domain recognition...

Please sign up or login with your details

Forgot password? Click here to reset