Paper Title:
ECAP: Extensive Cut-and-Paste Augmentation for Unsupervised Domain Adaptive Semantic Segmentation
Published on:
6 March 2024
Primary Category:
Computer Vision and Pattern Recognition
Paper Authors:
Erik Brorsson,
Knut Åkesson,
Lennart Svensson,
Kristofer Bengtsson
ECAP cut-and-pastes confident pseudo-labeled pixels onto training images
A memory bank stores target domain pseudo-labels during training
Sampling focuses on reliable pseudo-labels, reducing noise
Implemented on MIC model, ECAP advances state-of-the-art on Synthia->Cityscapes to 69.1 mIoU
Code is available at https://github.com/ErikBrorsson/ECAP
Extensive data augmentation for domain adaptation
This paper proposes a data augmentation strategy called ECAP to improve unsupervised domain adaptation for semantic segmentation. ECAP maintains a memory bank of target domain pseudo-labels over training. It selects the most confident pseudo-labels and cut-and-pastes them onto source domain images to augment the training data. This leverages reliable pseudo-labels and reduces the impact of erroneous ones. Implemented on the MIC model, ECAP reaches 69.1 mIoU on Synthia->Cityscapes, setting a new state-of-the-art.
Self-supervised camouflage segmentation
Domain adaptation for object detection across visual domains
Dual-domain image fusion for remote sensing semantic segmentation
Hybrid learning for event camera semantic segmentation
Model adaptation via collaborative training
Backpropagation-free adaptation for 3D test-time learning
No comments yet, be the first to start the conversation...
Sign up to comment on this paper