Susana Distancia Is All You Need: Enforcing Class Separability In Metric Learning Via Two Novel Distance-based Loss Functions For Few-shot Image Classification

Abstract

Few-shot learning is a challenging area of research that aims to learn new concepts with only a few labeled samples of data. Recent works based on metric-learning approaches leverage the meta-learning approach, which is encompassed by episodic tasks that make use a support (training) and query set (test) with the objective of learning a similarity comparison metric between those sets. Due to the lack of data, the learning process of the embedding network becomes an important part of the few-shot task. Previous works have addressed this problem using metric learning approaches, but the properties of the underlying latent space and the separability of the difference classes on it was not entirely enforced. In this work, we propose two different loss functions which consider the importance of the embedding vectors by looking at the intra-class and inter-class distance between the few data. The first loss function is the Proto-Triplet Loss, which is based on the original triplet loss with

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymendezruiz2023susana

Related papers

• Revisiting Metric Learning For Few-shot Image Classification (2019)14.90
• Finding Significant Features For Few-shot Learning Using Dimensionality Reduction (2021)2.26
• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• Constellation Loss: Improving The Efficiency Of Deep Metric Learning Loss Functions For Optimal Embedding (2019)0.00
• Rethinking Preventing Class-collapsing In Metric Learning With Margin-based Losses (2020)9.23
• Simpleshot: Revisiting Nearest-neighbor Classification For Few-shot Learning (2019)0.00
• Bsnet: Bi-similarity Network For Few-shot Fine-grained Image Classification (2020)20.42
• Episode-specific Fine-tuning For Metric-based Few-shot Learners With Optimization-based Training (2025)0.00