Inicio  /  Information  /  Vol: 12 Par: 1 (2021)  /  Artículo
ARTÍCULO
TITULO

Predicting the Generalization Ability of a Few-Shot Classifier

Myriam Bontonou    
Louis Béthune and Vincent Gripon    

Resumen

In the context of few-shot learning, one cannot measure the generalization ability of a trained classifier using validation sets, due to the small number of labeled samples. In this paper, we are interested in finding alternatives to answer the question: is my classifier generalizing well to new data? We investigate the case of transfer-based few-shot learning solutions, and consider three settings: (i) supervised where we only have access to a few labeled samples, (ii) semi-supervised where we have access to both a few labeled samples and a set of unlabeled samples and (iii) unsupervised where we only have access to unlabeled samples. For each setting, we propose reasonable measures that we empirically demonstrate to be correlated with the generalization ability of the considered classifiers. We also show that these simple measures can predict the generalization ability up to a certain confidence. We conduct our experiments on standard few-shot vision datasets.

 Artículos similares

       
 
Dragan Gataric, Nenad Ru?kic, Branko Aleksic, Tihomir Ðuric, Lato Pezo, Biljana Loncar and Milada Pezo    
Road traffic accidents are a significant public health issue, accounting for almost 1.3 million deaths worldwide annually, with millions more experiencing non-fatal injuries. A variety of subjective and objective factors contribute to the occurrence of t... ver más
Revista: Algorithms

 
Yingjie Wang, Qiang Tan, Desheng Wu, Hao Chen, Naikun Hu and Yuxuan Zhao    
In the deep well drilling process in the Fukang Depression of the Eastern Junggar Basin, rock fracturing issues and low rate of penetration (ROP) have posed significant challenges to drilling efficiency. Accurate predictions of ROP prior to drilling are ... ver más
Revista: Applied Sciences

 
Zihan Song, Sang-Ha Sung, Do-Myung Park and Byung-Kwon Park    
The core of dropout prediction lies in the selection of predictive models and feature tables. Machine learning models have been shown to predict student dropouts accurately. Because students may drop out of school in any semester, the student history dat... ver más
Revista: Applied Sciences

 
Lingfeng Zhong, Rui Liu, Xiaodong Miao, Yufeng Chen, Songhong Li and Haocheng Ji    
Compressors are important components in various power systems in the field of energy and power. In practical applications, compressors often operate under non-design conditions. Therefore, accurate calculation on performance under various operating condi... ver más
Revista: Aerospace

 
Seok-Ho Han, Husna Mutahira and Hoon-Seok Jang    
Ensuring food security has become of paramount importance due to the rising global population. In particular, the agriculture sector in South Korea faces several challenges such as an aging farming population and a decline in the labor force. These issue... ver más
Revista: Applied Sciences