paper-with-me

홈 › Papers

Leveraging the Feature Distribution in Transfer-based Few-Shot Learning

2020-06-06 · Yuqing Hu, Vincent Gripon, Stéphane Pateux

Few-shot classification is a challenging problem due to the uncertainty caused by using few labelled samples. In the past few years, many methods have been proposed to solve few-shot classification, among which transfer-based methods have proved to achieve the best performance. Following this vein, in this paper we propose a novel transfer-based method that builds on two successive steps: 1) preprocessing the feature vectors so that they become closer to Gaussian-like distributions, and 2) leveraging this preprocessing using an optimal-transport inspired algorithm (in the case of transductive settings). Using standardized vision benchmarks, we prove the ability of the proposed methodology to achieve state-of-the-art accuracy with various datasets, backbone architectures and few-shot settings.

📄 PDF Abstract BibTeX arXiv:2006.03806

Code (6)

yhu01/PT-MAP 공식 구현 pytorch
allenhaozhu/ease pytorch
mbonto/fewshot_neuroimaging_classification pytorch
sicara/easy-few-shot-learning pytorch
xiangyu8/PT-MAP-sf pytorch
yhu01/bms pytorch

Tasks

Few-Shot Image ClassificationFew-Shot LearningGeneral Classification

Similar Papers 제목 키워드 기반

Two-Level Adversarial Visual-Semantic Coupling for Generalized Zero-shot Learning

2020-07-15 · Shivam Chandhok, Vineeth N. Balasubramanian

The performance of generative zero-shot methods mainly depends on the quality of generated features and how well the model facilitates knowledge transfer between visual and semantic domains. The quality of generated feat…

Generalized Zero-Shot LearningRepresentation LearningTransfer LearningVocal Bursts Valence Prediction+1

Attribute Distribution Modeling and Semantic-Visual Alignment for Generative Zero-shot Learning

2026-03-06 · Haojie Pu, Zhuoming Li, Yongbiao Gao, Yuheng Jia arxiv

Generative zero-shot learning (ZSL) synthesizes features for unseen classes, leveraging semantic conditions to transfer knowledge from seen classes. However, it also introduces two intrinsic challenges: (1) class-level a…

Zero-Shot Learning

A Model of Two Tales: Dual Transfer Learning Framework for Improved Long-tail Item Recommendation

2020-10-29 · Yin Zhang, Derek Zhiyuan Cheng, Tiansheng Yao, Xinyang Yi 외

Highly skewed long-tail item distribution is very common in recommendation systems. It significantly hurts model performance on tail items. To improve tail-item recommendation, we conduct research to transfer knowledge f…

Data AugmentationRecommendation SystemsRepresentation LearningTransfer Learning

Transfer Learning for Power Outage Detection Task with Limited Training Data

2023-05-28 · Olukunle Owolabi

Early detection of power outages is crucial for maintaining a reliable power distribution system. This research investigates the use of transfer learning and language models in detecting outages with limited labeled data…

Few-Shot LearningTransfer Learning

Boosting Few-Shot Text Classification via Distribution Estimation

2023-03-26 · Han Liu, Feng Zhang, Xiaotong Zhang, Siyang Zhao 외

Distribution estimation has been demonstrated as one of the most effective approaches in dealing with few-shot image classification, as the low-level patterns and underlying representations can be easily transferred acro…

ClassificationFew-Shot Image ClassificationFew-Shot Text Classificationimage-classification+3