Multi-level Similarity Learning for Low-Shot Recognition

TL;DR

This paper introduces a multi-level similarity model for low-shot learning that captures image similarities at multiple levels to improve recognition of unseen classes with limited samples.

Contribution

The paper proposes a novel multi-level similarity learning approach that decomposes image similarity into image, global, and object levels for low-shot recognition.

Findings

Achieves promising results on Caltech-UCSD datasets.

Effective in 1-shot and 5-shot learning scenarios.

Outperforms existing methods in low-shot recognition tasks.

Abstract

Low-shot learning indicates the ability to recognize unseen objects based on very limited labeled training samples, which simulates human visual intelligence. According to this concept, we propose a multi-level similarity model (MLSM) to capture the deep encoded distance metric between the support and query samples. Our approach is achieved based on the fact that the image similarity learning can be decomposed into image-level, global-level, and object-level. Once the similarity function is established, MLSM will be able to classify images for unseen classes by computing the similarity scores between a limited number of labeled samples and the target images. Furthermore, we conduct 5-way experiments with both 1-shot and 5-shot setting on Caltech-UCSD datasets. It is demonstrated that the proposed model can achieve promising results compared with the existing methods in practical applications.