cross-domain few-shot learning
31 papers with code • 1 benchmarks • 1 datasets
Its essence is transfer learning. The model needs to be trained in the source domain and then migrated to the target domain. Compliant with (1) the category in the target domain has never appeared in the source domain (2) the data distribution of the target domain is inconsistent with the source domain (3) each class in the target domain has very few labels
Benchmarks
These leaderboards are used to track progress in cross-domain few-shot learning
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
Office-Home
Latest papers
Discriminative Sample-Guided and Parameter-Efficient Feature Space Adaptation for Cross-Domain Few-Shot Learning
rashindrie/dipa
•
•
In this paper, we look at cross-domain few-shot classification which presents the challenging task of learning new classes in previously unseen domains with few labelled examples.
Enhancing Information Maximization with Distance-Aware Contrastive Learning for Source-Free Cross-Domain Few-Shot Learning
For this reason, this paper explores a Source-Free CDFSL (SF-CDFSL) problem, in which CDFSL is addressed through the use of existing pretrained models instead of training a model with source data, avoiding accessing source data.
Cross-Domain Few-Shot Learning via Adaptive Transformer Networks
Most few-shot learning works rely on the same domain assumption between the base and the target tasks, hindering their practical applications.
Leveraging Normalization Layer in Adapters With Progressive Learning and Adaptive Distillation for Cross-Domain Few-Shot Learning
YangYongJin/APEX
•
•
Second, to address the pitfalls of noisy statistics, we deploy two strategies: a progressive training of the two adapters and an adaptive distillation technique derived from features determined by the model solely with the adapter devoid of a normalization layer.
Multi-level Relation Learning for Cross-domain Few-shot Hyperspectral Image Classification
henulwy/stbdip
•
•
In addition, it adopts a transformer based cross-attention learning module to learn the set-level sample relations and acquire the attention from query samples to support samples.
Domain Adaptive Few-Shot Open-Set Learning
debabratapal7/dafosnet
•
•
ICCV 2023
Few-shot learning has made impressive strides in addressing the crucial challenges of recognizing unknown samples from novel classes in target query sets and managing visual shifts between domains.
CDFSL-V: Cross-Domain Few-Shot Learning for Videos
sarinda251/cdfsl-v
•
•
ICCV 2023
To address this issue, in this work, we propose a novel cross-domain few-shot video action recognition method that leverages self-supervised learning and curriculum learning to balance the information from the source and target domains.
Dual Adaptive Representation Alignment for Cross-domain Few-shot Learning
icvteam/dara
•
•
Recent progress in this setting assumes that the base knowledge and novel query samples are distributed in the same domains, which are usually infeasible for realistic applications.
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.
Revisiting Prototypical Network for Cross Domain Few-Shot Learning
nwpuzhoufei/ldp-net
•
•
CVPR 2023
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.
