Unsupervised descriptor selection based meta-learning networks for few-shot classification

We propose a method that can perform one-class classification given only a small number of examples from the target class and none from the others. We formulate the learning of meaningful features for one-class classification as a meta-learning problem in which the meta-training stage repeatedly simulates one-class classification, using the classification loss of the chosen algorithm to learn a feature representation. To learn these representations, we require only multiclass data from similar tasks. We show how the Support Vector Data Description method can be used with our method, and also propose a simpler variant based on Prototypical Networks that obtains comparable performance, indicating that learning feature representations directly from data may be more important than which one-class algorithm we choose. We validate our approach by adapting few-shot classification datasets to the few-shot one-class classification scenario, obtaining similar results to the state-of-the-art of traditional one-class classification, and that improves upon that of one-class classification baselines employed in the few-shot setting.

Download Full-text

Few-Shot Classification in Unseen Domains by Episodic Meta-Learning Across Visual Domains

10.1109/icip42928.2021.9506141 ◽

2021 ◽

Author(s):

Yuan-Chia Cheng ◽

Ci-Siang Lin ◽

Fu-En Yang ◽

Yu-Chiang Frank Wang

Keyword(s):

Shot Classification ◽

Meta Learning

Download Full-text

Semi-supervised meta-learning networks with squeeze-and-excitation attention for few-shot fault diagnosis

ISA Transactions ◽

10.1016/j.isatra.2021.03.013 ◽

2021 ◽

Author(s):

Yong Feng ◽

Jinglong Chen ◽

Tianci Zhang ◽

Shuilong He ◽

Enyong Xu ◽

...

Keyword(s):

Fault Diagnosis ◽

Learning Networks ◽

Meta Learning

Download Full-text

IMAL: An Improved Meta-learning Approach for Few-shot Classification of Plant Diseases

10.1109/bibe52308.2021.9635575 ◽

2021 ◽

Author(s):

Yingtao Wang ◽

Shunfang Wang

Keyword(s):

Plant Diseases ◽

Learning Approach ◽

Shot Classification ◽

Meta Learning

Download Full-text

Fast Few-Shot Classification by Few-Iteration Meta-Learning

10.1109/icra48506.2021.9561269 ◽

2021 ◽

Author(s):

Ardhendu Shekhar Tripathi ◽

Martin Danelljan ◽

Luc Van Gool ◽

Radu Timofte

Keyword(s):

Shot Classification ◽

Meta Learning

Download Full-text

Prototype Propagation Networks (PPN) for Weakly-supervised Few-shot Learning on Category Graph

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/418 ◽

2019 ◽

Cited By ~ 9

Author(s):

Lu Liu ◽

Tianyi Zhou ◽

Guodong Long ◽

Jing Jiang ◽

Lina Yao ◽

...

Keyword(s):

Nearest Neighbor ◽

Common Knowledge ◽

K Nearest Neighbor ◽

Shot Classification ◽

Meta Learning ◽

Machine Learning Applications ◽

Weakly Supervised ◽

Propagation Network ◽

Training Objective ◽

Weakly Labeled Data

A variety of machine learning applications expect to achieve rapid learning from a limited number of labeled data. However, the success of most current models is the result of heavy training on big data. Meta-learning addresses this problem by extracting common knowledge across different tasks that can be quickly adapted to new tasks. However, they do not fully explore weakly-supervised information, which is usually free or cheap to collect. In this paper, we show that weakly-labeled data can significantly improve the performance of meta-learning on few-shot classification. We propose prototype propagation network (PPN) trained on few-shot tasks together with data annotated by coarse-label. Given a category graph of the targeted fine-classes and some weakly-labeled coarse-classes, PPN learns an attention mechanism which propagates the prototype of one class to another on the graph, so that the K-nearest neighbor (KNN) classifier defined on the propagated prototypes results in high accuracy across different few-shot tasks. The training tasks are generated by subgraph sampling, and the training objective is obtained by accumulating the level-wise classification loss on the subgraph. On two benchmarks, PPN significantly outperforms most recent few-shot learning methods in different settings, even when they are also allowed to train on weakly-labeled data.

Download Full-text

Few-shot Classification of Aerial Scene Images via Meta-learning

10.20944/preprints202010.0033.v1 ◽

2020 ◽

Cited By ~ 1

Author(s):

Pei Zhang ◽

YIng Li ◽

Dong Wang ◽

Yunpeng Bai

Keyword(s):

Classification Problem ◽

Training Data ◽

Scene Classification ◽

Shot Classification ◽

Training Stage ◽

Testing Stage ◽

Meta Learning ◽

Cosine Distance ◽

Query Sample

CNN-based methods have dominated the field of aerial scene classification for the past few years. While achieving remarkable success, CNN-based methods suffer from excessive parameters and notoriously rely on large amounts of training data. In this work, we introduce few-shot learning to the aerial scene classification problem. Few-shot learning aims to learn a model on base-set that can quickly adapt to unseen categories in novel-set, using only a few labeled samples. To this end, we proposed a meta-learning method for few-shot classification of aerial scene images. First, we train a feature extractor on all base categories to learn a representation of inputs. Then in the meta-training stage, the classifier is optimized in the metric space by cosine distance with a learnable scale parameter. At last, in the meta-testing stage, the query sample in the unseen category is predicted by the adapted classifier given a few support samples. We conduct extensive experiments on two challenging datasets: NWPU-RESISC45 and RSD46-WHU. The experimental results show that our method outperforms three state-of-the-art few-shot algorithms and one typical CNN-based method, D-CNN. Furthermore, several ablation experiments are conducted to investigate the effects of dataset scale and support shots; the experiment results confirm that our model is specifically effective in few-shot settings.

Download Full-text

Meta-FSEO: A Meta-Learning Fast Adaptation with Self-Supervised Embedding Optimization for Few-Shot Remote Sensing Scene Classification

Remote Sensing ◽

10.3390/rs13142776 ◽

2021 ◽

Vol 13 (14) ◽

pp. 2776

Author(s):

Yong Li ◽

Zhenfeng Shao ◽

Xiao Huang ◽

Bowen Cai ◽

Song Peng

Keyword(s):

Remote Sensing ◽

Deep Learning ◽

Remote Sensing Data ◽

Scene Classification ◽

Generalization Capability ◽

Urban Scenes ◽

Shot Classification ◽

Meta Learning ◽

Land Surfaces ◽

Fast Adaptation

The performance of deep learning is heavily influenced by the size of the learning samples, whose labeling process is time consuming and laborious. Deep learning algorithms typically assume that the training and prediction data are independent and uniformly distributed, which is rarely the case given the attributes and properties of different data sources. In remote sensing images, representations of urban land surfaces can vary across regions and by season, demanding rapid generalization of these surfaces in remote sensing data. In this study, we propose Meta-FSEO, a novel model for improving the performance of few-shot remote sensing scene classification in varying urban scenes. The proposed Meta-FSEO model deploys self-supervised embedding optimization for adaptive generalization in new tasks such as classifying features in new urban regions that have never been encountered during the training phase, thus balancing the requirements for feature classification tasks between multiple images collected at different times and places. We also created a loss function by weighting the contrast losses and cross-entropy losses. The proposed Meta-FSEO demonstrates a great generalization capability in remote sensing scene classification among different cities. In a five-way one-shot classification experiment with the Sentinel-1/2 Multi-Spectral (SEN12MS) dataset, the accuracy reached 63.08%. In a five-way five-shot experiment on the same dataset, the accuracy reached 74.29%. These results indicated that the proposed Meta-FSEO model outperformed both the transfer learning-based algorithm and two popular meta-learning-based methods, i.e., MAML and Meta-SGD.

Download Full-text