Multi-Scale Adaptive Task Attention Network for Few-Shot Learning

Chen, Haoxing; Li, Huaxiong; Li, Yaohui; Chen, Chunlin

doi:10.1109/icpr56361.2022.9955637

Cited by 12 publications

(1 citation statement)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The main objective of these methods is to learn an effective embedding network in order to extract useful features of the task and discriminate on the classes which we are trying to predict. From this basic learning, there have been many extensions proposed to improve the performance of metric learning methods, some of those focus on pre-training the embedding network [2], task attention modules [3,12,21], optimization of embeddings [11] and use of different loss functions [21].…”

Section: Introductionmentioning

confidence: 99%

Finding Significant Features for Few-Shot Learning using Dimensionality Reduction Techniques

Mendez¹,

García²,

Méndez-Vázquez³

et al. 2021

LatinX in AI at Computer Vision and Pattern Recognition Conference 2021

View full text Add to dashboard Cite

ew-shot learning is a fairly new technique that specialize in problems where we have little amount of data. The goal of this method is to classify categories that hasn’t been seen before with just a handful of samples. Recent approaches, such as metric learning, adopt the meta-learning setting in which we have episodic tasks conformed by support (training) data and query (test) data. Metric learning methods has demonstrated that simple models can achieve good performance, by learning a similarity function to compare the support and the query data. However, the feature space learned by the metric learning may not exploit the information given by a specific few-shot task. In this work, we explore the use of dimension reduction techniques as a way to find task significant features. We measure the performance of the reduced features by giving a score based on the intra-class and inter-class distance, and select the method in which instances of different classes are distant and instances of the same class are close. This module helps to improve the accuracy performance by allowing the similarity function, given by the metric learning method, to have more discriminative features for the classification.

show abstract