Mutually-Aware Feature Learning for Few-Shot Object Counting

TL;DR

This paper introduces MAFEA, a mutual-aware feature learning framework for few-shot object counting that enhances target recognition by enabling continuous interaction between query and exemplar features, leading to state-of-the-art results.

Contribution

The paper proposes a novel mutual-aware feature learning framework that improves few-shot object counting by fostering continuous interaction between query and exemplar features.

Findings

Achieves state-of-the-art performance on FSCD-LVIS and FSC-147 benchmarks.

Reduces target confusion significantly in multi-category scenarios.

Effectively associates target regions with exemplars using background tokens.

Abstract

Few-shot object counting has garnered significant attention for its practicality as it aims to count target objects in a query image based on given exemplars without additional training. However, the prevailing extract-and-match approach has a shortcoming: query and exemplar features lack interaction during feature extraction since they are extracted independently and later correlated based on similarity. This can lead to insufficient target awareness and confusion in identifying the actual target when multiple class objects coexist. To address this, we propose a novel framework, Mutually-Aware FEAture learning (MAFEA), which encodes query and exemplar features with mutual awareness from the outset. By encouraging interaction throughout the pipeline, we obtain target-aware features robust to a multi-category scenario. Furthermore, we introduce background token to effectively associate the query's target region with exemplars and decouple its background region. Our extensive experiments demonstrate that our model achieves state-of-the-art performance on FSCD-LVIS and FSC-147 benchmarks with remarkably reduced target confusion.