MSI: Maximize Support-Set Information for Few-Shot Segmentation

TL;DR

MSI enhances few-shot segmentation by maximizing support-set information through dual feature sources, overcoming limitations of support mask-based feature removal, leading to improved accuracy and faster convergence.

Contribution

Introduces MSI, a novel approach that exploits two feature sources to generate super correlation maps, improving few-shot segmentation performance.

Findings

Consistently improves performance across multiple benchmarks.

Achieves faster convergence in training.

Effective in challenging scenarios with small targets or boundary inaccuracies.

Abstract

FSS(Few-shot segmentation) aims to segment a target class using a small number of labeled images(support set). To extract information relevant to the target class, a dominant approach in best-performing FSS methods removes background features using a support mask. We observe that this feature excision through a limiting support mask introduces an information bottleneck in several challenging FSS cases, e.g., for small targets and/or inaccurate target boundaries. To this end, we present a novel method(MSI), which maximizes the support-set information by exploiting two complementary sources of features to generate super correlation maps. We validate the effectiveness of our approach by instantiating it into three recent and strong FSS methods. Experimental results on several publicly available FSS benchmarks show that our proposed method consistently improves performance by visible margins and leads to faster convergence. Our code and trained models are available at: https://github.com/moonsh/MSI-Maximize-Support-Set-Information