DMN4: Few-shot Learning via Discriminative Mutual Nearest Neighbor Neural Network

TL;DR

DMN4 introduces a discriminative mutual nearest neighbor approach that selectively utilizes relevant local features for improved few-shot learning performance, effectively filtering out irrelevant descriptors.

Contribution

The paper proposes a novel DMN4 method that explicitly establishes mutual nearest neighbor relations to select task-relevant descriptors, enhancing few-shot learning accuracy.

Findings

Outperforms state-of-the-art methods on fine-grained datasets

Effective in both fine-grained and generalized few-shot learning tasks

Demonstrates robustness by filtering irrelevant descriptors

Abstract

Few-shot learning (FSL) aims to classify images under low-data regimes, where the conventional pooled global feature is likely to lose useful local characteristics. Recent work has achieved promising performances by using deep descriptors. They generally take all deep descriptors from neural networks into consideration while ignoring that some of them are useless in classification due to their limited receptive field, e.g., task-irrelevant descriptors could be misleading and multiple aggregative descriptors from background clutter could even overwhelm the object's presence. In this paper, we argue that a Mutual Nearest Neighbor (MNN) relation should be established to explicitly select the query descriptors that are most relevant to each task and discard less relevant ones from aggregative clutters in FSL. Specifically, we propose Discriminative Mutual Nearest Neighbor Neural Network (DMN4) for FSL. Extensive experiments demonstrate that our method outperforms the existing state-of-the-arts on both fine-grained and generalized datasets.