IPEC: Test-Time Incremental Prototype Enhancement Classifier for Few-Shot Learning

TL;DR

The paper introduces IPEC, a test-time incremental prototype enhancement method for few-shot learning that leverages previous query samples to improve prototype estimation and classification accuracy.

Contribution

IPEC is a novel test-time approach that dynamically updates prototypes using a dual-filtering mechanism and Bayesian interpretation, enhancing few-shot learning performance.

Findings

IPEC outperforms existing methods on multiple few-shot classification benchmarks.

The dual-filtering mechanism effectively selects high-quality query samples.

Prototype stability improves with auxiliary set aggregation over tasks.

Abstract

Metric-based few-shot approaches have gained significant popularity due to their relatively straightforward implementation, high interpret ability, and computational efficiency. However, stemming from the batch-independence assumption during testing, which prevents the model from leveraging valuable knowledge accumulated from previous batches. To address these challenges, we propose a novel test-time method called Incremental Prototype Enhancement Classifier (IPEC), a test-time method that optimizes prototype estimation by leveraging information from previous query samples. IPEC maintains a dynamic auxiliary set by selectively incorporating query samples that are classified with high confidence. To ensure sample quality, we design a robust dual-filtering mechanism that assesses each query sample based on both global prediction confidence and local discriminative ability. By aggregating this auxiliary set with the support set in subsequent tasks, IPEC builds progressively more stable and representative prototypes, effectively reducing its reliance on the initial support set. We ground this approach in a Bayesian interpretation, conceptualizing the support set as a prior and the auxiliary set as a data-driven posterior, which in turn motivates the design of a practical "warm-up and test" two-stage inference protocol. Extensive empirical results validate the superior performance of our proposed method across multiple few-shot classification tasks.