Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder

Liang, Hanwen; Zhang, Qiong; Dai, Peng; Lu, Juwei

doi:10.1109/iccv48922.2021.00929

Cited by 52 publications

(24 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Typically, CD-FSL with only source data is the most strict setting that demands model to recognize totally unseen target dataset without any target information. Flagship works including FWT [44], BSCD-FSL [18], LRP [40], ATA [48], wave-SAN [14], RDC [29], NSAE [32], and ConFT [10]. Though many well-designed techniques e.g.…”

Section: Related Workmentioning

confidence: 99%

“…Though many well-designed techniques e.g. readjusting the batch normalization [44], augmenting the difficult of meta tasks [48], spanning style distributions [14], and even fine-tuning models using few target images during the testing stage [10,18,29,32], the performances of them are still greatly limited due to the huge domain gap. By contrast, STARTUP [33] relaxes this strict setting and uses unlabeled target data for training.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

Xie

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

Recently, Cross-Domain Few-Shot Learning (CD-FSL) which aims at addressing the Few-Shot Learning (FSL) problem across different domains has attracted rising attention. The core challenge of CD-FSL lies in the domain gap between the source and novel target datasets. Though many attempts have been made for CD-FSL without any target data during model training, the huge domain gap makes it still hard for existing CD-FSL methods to achieve very satisfactory results. Alternatively, learning CD-FSL models with few labeled target domain data which is more realistic and promising is advocated in previous work [13]. Thus, in this paper, we stick to this setting and technically contribute a novel Multi-Expert Domain Decompositional Network (ME-D2N). Concretely, to solve the data imbalance problem between the source data with sufficient examples and the auxiliary target data with limited examples, we build our model under the umbrella of multi-expert * indicates equal contributions, # indicates corresponding author.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

Xie

et al. 2022

Proceedings of the 30th ACM International Conference on Multimedia

View full text Add to dashboard Cite

show abstract

“…Our approach also follows the pre-training paradigm, and we further expect the learned representations to be compact and cross-domain aligned to address the CDCS-FSL problem. CD-FSL [15,42,29,47,22,14,10] considers the domain shift problem between the base classes and the novel classes. Due to such domain gap, [4] show that meta-learning approaches fail to adapt to novel classes.…”

Section: Related Workmentioning

confidence: 99%

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

Chen¹,

Zhang²,

Wang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Few-shot learning (FSL) aims to recognize novel queries with only a few support samples through leveraging prior knowledge from a base dataset. In this paper, we consider the domain shift problem in FSL and aim to address the domain gap between the support set and the query set. Different from previous cross-domain FSL work (CD-FSL) that considers the domain shift between base and novel classes, the new problem, termed cross-domain cross-set FSL (CDSC-FSL), requires fewshot learners not only to adapt to the new domain, but also to be consistent between different domains within each novel class. To this end, we propose a novel approach, namely stabPA, to learn prototypical compact and cross-domain aligned representations, so that the domain shift and few-shot learning can be addressed simultaneously. We evaluate our approach on two new CDCS-FSL benchmarks built from the Domain-Net and Office-Home datasets respectively. Remarkably, our approach outperforms multiple elaborated baselines by a large margin, e.g., improving 5-shot accuracy by 6.0 points on average on DomainNet. Code is available at https://github.com/WentaoChen0813/CDCS-FSL.

show abstract

“…To make matters worse, most DL methods in the state of the art still require humongous amounts of data to be trained, which is not realistic in most of the medical application domains. Therefore, in recent years, the meta-learning and Few-Shot Learning (FSL) paradigms have emerged as a means to cope with the training data scarcity problem and furthermore, to make models more capable of generalization with less computing effort and incremental learning capabilities [28].…”

Section: Introductionmentioning

confidence: 99%

On the generalization capabilities of FSL methods through domain adaptation: a case study in endoscopic kidney stone image classification

Mendez-Ruiz¹,

Lopez-Tiro²,

Jonathan³

et al. 2022

Preprint

View full text Add to dashboard Cite

Deep learning has shown great promise in diverse areas of computer vision, such as image classification, object detection and semantic segmentation, among many others. However, as it has been repeatedly demonstrated, deep learning methods trained on a dataset do not generalize well to datasets from other domains or even to similar datasets, due to data distribution shifts. In this work, we propose the use of a meta-learning based few-shot learning approach to alleviate these problems. In order to demonstrate its efficacy, we use two datasets of kidney stones samples acquired with different endoscopes and different acquisition conditions. The results show how such methods are indeed capable of handling domainshifts by attaining an accuracy of 74.38% and 88.52% in the 5-way 5-shot and 5-way 20-shot settings respectively. Instead, in the same dataset, traditional Deep Learning (DL) methods attain only an accuracy of 45%.

show abstract

Boosting the Generalization Capability in Cross-Domain Few-shot Learning via Noise-enhanced Supervised Autoencoder

Cited by 52 publications

References 25 publications

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

ME-D2N: Multi-Expert Domain Decompositional Network for Cross-Domain Few-Shot Learning

Cross-Domain Cross-Set Few-Shot Learning via Learning Compact and Aligned Representations

On the generalization capabilities of FSL methods through domain adaptation: a case study in endoscopic kidney stone image classification

Contact Info

Product

Resources

About