Papers Unsupervised Few-Shot Image Classification

“Unsupervised Few-Shot Image Classification” 태그가 달린 논문 28편 · 필터 해제

Unsupervised Meta-Learning through Latent-Space Interpolation in Generative Models

2020-06-18 · ICLR 2021 1 · Siavash Khodadadeh, Sharare Zehtabian, Saeed Vahidian, Weijia Wang 외

Unsupervised meta-learning approaches rely on synthetic meta-tasks that are created using techniques such as random selection, clustering and/or augmentation. Unfortunately, clustering and augmentation are domain-depende…

Clustering Meta-Learning Unsupervised Few-Shot Image Classification

Diversity Helps: Unsupervised Few-shot Learning via Distribution Shift-based Data Augmentation

2020-04-13 · Tiexin Qin, Wenbin Li, Yinghuan Shi, Yang Gao

Few-shot learning aims to learn a new concept when only a few training examples are available, which has been extensively explored in recent years. However, most of the current works heavily rely on a large-scale labeled…

Data Augmentation Diversity Few-Shot Learning Unsupervised Few-Shot Image Classification+1

Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning

2020-01-12 · CVPR 2021 1 · Hongguang Zhang, Piotr Koniusz, Songlei Jian, Hongdong Li 외

The majority of existing few-shot learning methods describe image relations with binary labels. However, such binary relations are insufficient to teach the network complicated real-world relations, due to the lack of de…

Few-Shot Learning Relation Unsupervised Few-Shot Image Classification Unsupervised Few-Shot Learning

Unsupervised Few-shot Learning via Self-supervised Training

2019-12-20 · Zilong Ji, Xiaolong Zou, Tiejun Huang, Si Wu

Learning from limited exemplars (few-shot learning) is a fundamental, unsolved problem that has been laboriously explored in the machine learning community. However, current few-shot learners are mostly supervised and re…

BIG-bench Machine Learning Clustering Few-Shot Learning Person Re-Identification+2

Self-Supervised Learning For Few-Shot Image Classification

2019-11-14 · Da Chen, Yuefeng Chen, Yuhong Li, Feng Mao 외

Few-shot image classification aims to classify unseen classes with limited labelled samples. Recent works benefit from the meta-learning process with episodic tasks and can fast adapt to class from training to testing. D…

Classification Cross-Domain Few-Shot cross-domain few-shot learning Few-Shot Image Classification+7

Assume, Augment and Learn: Unsupervised Few-Shot Meta-Learning via Random Labels and Data Augmentation

2019-02-26 · Antreas Antoniou, Amos Storkey

The field of few-shot learning has been laboriously explored in the supervised setting, where per-class labels are available. On the other hand, the unsupervised few-shot learning setting, where no labels of any kind are…

Data Augmentation Few-Shot Learning Meta-Learning Unsupervised Few-Shot Image Classification+1

Unsupervised Meta-Learning For Few-Shot Image Classification

2018-11-28 · NeurIPS 2019 12 · Siavash Khodadadeh, Ladislau Bölöni, Mubarak Shah

Few-shot or one-shot learning of classifiers requires a significant inductive bias towards the type of task to be learned. One way to acquire this is by meta-learning on tasks similar to the target task. In this paper, w…

Classification Few-Shot Image Classification Few-Shot Learning General Classification+8

Unsupervised Learning via Meta-Learning

2018-10-04 · ICLR 2019 5 · Kyle Hsu, Sergey Levine, Chelsea Finn

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior uns…

Clustering Disentanglement Meta-Learning Unsupervised Few-Shot Image Classification+1