Episode-specific Fine-tuning For Metric-based Few-shot Learners With Optimization-based Training

Abstract

In few-shot classification tasks (so-called episodes), a small set of labeled support samples is provided during inference to aid the classification of unlabeled query samples. Metric-based models typically operate by computing similarities between query and support embeddings within a learned metric space, followed by nearest-neighbor classification. However, these labeled support samples are often underutilized--they are only used for similarity comparison, despite their potential to fine-tune and adapt the metric space itself to the classes in the current episode. To address this, we propose a series of simple yet effective episode-specific, during-inference fine-tuning methods for metric-based models, including Rotational Division Fine-Tuning (RDFT) and its two variants, Iterative Division Fine-Tuning (IDFT) and Augmented Division Fine-Tuning (ADFT). These methods construct pseudo support-query pairs from the given support set to enable fine-tuning even for non-parametric models. N

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhuang2025episode

Related papers

• Few-shot Metric Learning: Online Adaptation Of Embedding For Retrieval (2022)8.09
• 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
• Finding Significant Features For Few-shot Learning Using Dimensionality Reduction (2021)2.26
• Revisiting Metric Learning For Few-shot Image Classification (2019)14.90
• Ndpnet: A Novel Non-linear Data Projection Network For Few-shot Fine-grained Image Classification (2021)0.00
• Few-shot Learning Through An Information Retrieval Lens (2017)0.00
• Dynamic Sampling For Deep Metric Learning (2020)5.84
• Dynamic Metric Learning From Pairwise Comparisons (2016)3.58