HM: Hybrid Masking for Few-Shot Segmentation

TL;DR

This paper introduces Hybrid Masking (HM), an improved method for few-shot segmentation that combines feature masking with input masking to better preserve spatial details and enhance segmentation accuracy.

Contribution

The paper proposes a novel hybrid masking technique that effectively combines feature and input masking to improve few-shot segmentation performance.

Findings

HM outperforms state-of-the-art methods on three benchmarks.

Hybrid masking significantly improves segmentation of small objects.

The approach is simple, effective, and computationally efficient.

Abstract

We study few-shot semantic segmentation that aims to segment a target object from a query image when provided with a few annotated support images of the target class. Several recent methods resort to a feature masking (FM) technique to discard irrelevant feature activations which eventually facilitates the reliable prediction of segmentation mask. A fundamental limitation of FM is the inability to preserve the fine-grained spatial details that affect the accuracy of segmentation mask, especially for small target objects. In this paper, we develop a simple, effective, and efficient approach to enhance feature masking (FM). We dub the enhanced FM as hybrid masking (HM). Specifically, we compensate for the loss of fine-grained spatial details in FM technique by investigating and leveraging a complementary basic input masking method. Experiments have been conducted on three publicly available benchmarks with strong few-shot segmentation (FSS) baselines. We empirically show improved performance against the current state-of-the-art methods by visible margins across different benchmarks. Our code and trained models are available at: https://github.com/moonsh/HM-Hybrid-Masking