Finding Significant Features For Few-shot Learning Using Dimensionality Reduction

Abstract

Few-shot learning is a relatively new technique that specializes in problems where we have little amounts of data. The goal of these methods is to classify categories that have not been seen before with just a handful of samples. Recent approaches, such as metric learning, adopt the meta-learning strategy in which we have episodic tasks conformed by support (training) data and query (test) data. Metric learning methods have 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 a given metric learning approach 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 helping to make better predictions. We measure the performance of the reduced features by assigning a score based on the intra-class and inter-class distance, and selecting a feature red

Stats

• citations1
• S2 citations—
• github stars0
• HF likes0
• heat score2.26
• arxiv keymendezruiz2021finding

Related papers

• Revisiting Metric Learning For Few-shot Image Classification (2019)14.90
• Simpleshot: Revisiting Nearest-neighbor Classification For Few-shot Learning (2019)0.00
• Susana Distancia Is All You Need: Enforcing Class Separability In Metric Learning Via Two Novel Distance-based Loss Functions For Few-shot Image Classification (2023)0.00
• Few-shot Learning Through An Information Retrieval Lens (2017)0.00
• Episode-specific Fine-tuning For Metric-based Few-shot Learners With Optimization-based Training (2025)0.00
• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• Ranking Distance Calibration For Cross-domain Few-shot Learning (2021)12.93
• Ndpnet: A Novel Non-linear Data Projection Network For Few-shot Fine-grained Image Classification (2021)0.00