Cross-Domain Few-Shot
55 papers with code • 9 benchmarks • 6 datasets
Benchmarks
These leaderboards are used to track progress in Cross-Domain Few-Shot
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Cross-Domain Few-Shot models and implementations
CUB-200-2011
mini-Imagenet
Places
Places205
EuroSAT
Earth on Canvas
Most implemented papers
StyleAdv: Meta Style Adversarial Training for Cross-Domain Few-Shot Learning
lovelyqian/styleadv-cdfsl
•
•
CVPR 2023
Thus, inspired by vanilla adversarial learning, a novel model-agnostic meta Style Adversarial training (StyleAdv) method together with a novel style adversarial attack method is proposed for CD-FSL.
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
hytseng0509/CrossDomainFewShot
•
•
ICLR 2020
Few-shot classification aims to recognize novel categories with only few labeled images in each class.
A Transductive Multi-Head Model for Cross-Domain Few-Shot Learning
leezhp1994/TMHFS
•
•
The TMHFS method extends the Meta-Confidence Transduction (MCT) and Dense Feature-Matching Networks (DFMN) method [2] by introducing a new prediction head, i. e, an instance-wise global classification network based on semantic information, after the common feature embedding network.
Explanation-Guided Training for Cross-Domain Few-Shot Classification
SunJiamei/few-shot-lrp-guided
•
•
It leverages on the explanation scores, obtained from existing explanation methods when applied to the predictions of FSC models, computed for intermediate feature maps of the models.
Few-Shot Classification with Feature Map Reconstruction Networks
Tsingularity/FRN
•
•
CVPR 2021
In this paper we reformulate few-shot classification as a reconstruction problem in latent space.
Few-shot Image Classification: Just Use a Library of Pre-trained Feature Extractors and a Simple Classifier
arjish/PreTrainedFullLibrary_FewShot
•
•
ICCV 2021
Recent papers have suggested that transfer learning can outperform sophisticated meta-learning methods for few-shot image classification.
Modular Adaptation for Cross-Domain Few-Shot Learning
Adapting pre-trained representations has become the go-to recipe for learning new downstream tasks with limited examples.
Cross-Domain Few-Shot Classification via Adversarial Task Augmentation
However, when there exists the domain shift between the training tasks and the test tasks, the obtained inductive bias fails to generalize across domains, which degrades the performance of the meta-learning models.
DAMSL: Domain Agnostic Meta Score-based Learning
johncai117/DAMSL
•
•
In this paper, we propose Domain Agnostic Meta Score-based Learning (DAMSL), a novel, versatile and highly effective solution that delivers significant out-performance over state-of-the-art methods for cross-domain few-shot learning.
Dynamic Distillation Network for Cross-Domain Few-Shot Recognition with Unlabeled Data
asrafulashiq/dynamic-cdfsl
•
•
NeurIPS 2021
As the base dataset and unlabeled dataset are from different domains, projecting the target images in the class-domain of the base dataset with a fixed pretrained model might be sub-optimal.
