Deep learning for cross-domain few-shot visual recognition: A survey

H Xu, S Zhi, S Sun, VM Patel, L Liu - arxiv preprint arxiv:2303.08557, 2023 - arxiv.org
Deep learning has been highly successful in computer vision with large amounts of labeled
data, but struggles with limited labeled training data. To address this, Few-shot learning …

Trustworthy representation learning across domains

R Zhu, D Guo, D Qi, Z Chu, X Yu, S Li - arxiv preprint arxiv:2308.12315, 2023 - arxiv.org
As AI systems have obtained significant performance to be deployed widely in our daily live
and human society, people both enjoy the benefits brought by these technologies and suffer …

Taxonomy adaptive cross-domain adaptation in medical imaging via optimization trajectory distillation

J Fan, D Liu, H Chang, H Huang… - Proceedings of the …, 2023 - openaccess.thecvf.com
The success of automated medical image analysis depends on large-scale and expert-
annotated training sets. Unsupervised domain adaptation (UDA) has been raised as a …

Deta: Denoised task adaptation for few-shot learning

J Zhang, L Gao, X Luo, H Shen… - Proceedings of the …, 2023 - openaccess.thecvf.com
Test-time task adaptation in few-shot learning aims to adapt a pre-trained task-agnostic
model for capturing task-specific knowledge of the test task, rely only on few-labeled support …

Point cloud domain adaptation via masked local 3d structure prediction

H Liang, H Fan, Z Fan, Y Wang, T Chen… - … on Computer Vision, 2022 - Springer
The superiority of deep learning based point cloud representations relies on large-scale
labeled datasets, while the annotation of point clouds is notoriously expensive. One of the …

Styleadv: Meta style adversarial training for cross-domain few-shot learning

Y Fu, Y **e, Y Fu, YG Jiang - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Abstract Cross-Domain Few-Shot Learning (CD-FSL) is a recently emerging task that tackles
few-shot learning across different domains. It aims at transferring prior knowledge learned …

Dual contrastive network for few-shot remote sensing image scene classification

Z Ji, L Hou, X Wang, G Wang… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Few-shot remote sensing image scene classification (FS-RSISC) aims at classifying remote
sensing images with only a few labeled samples. The main challenges lie in small interclass …

Dual attention relation network with fine-tuning for few-shot EEG motor imagery classification

S An, S Kim, P Chikontwe… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Recently, motor imagery (MI) electroencephalography (EEG) classification techniques using
deep learning have shown improved performance over conventional techniques. However …

Revisiting prototypical network for cross domain few-shot learning

F Zhou, P Wang, L Zhang, W Wei… - Proceedings of the …, 2023 - openaccess.thecvf.com
Prototypical Network is a popular few-shot solver that aims at establishing a feature metric
generalizable to novel few-shot classification (FSC) tasks using deep neural networks …

Ranking distance calibration for cross-domain few-shot learning

P Li, S Gong, C Wang, Y Fu - Proceedings of the IEEE/CVF …, 2022 - openaccess.thecvf.com
Recent progress in few-shot learning promotes a more realistic cross-domain setting, where
the source and target datasets are in different domains. Due to the domain gap and disjoint …