Improving 3D Few-Shot Segmentation with Inference-Time Pseudo-Labeling

TL;DR

This paper introduces a novel inference-time pseudo-labeling method that leverages query information to improve 3D few-shot segmentation accuracy, especially in medical imaging, by iteratively refining support sets with confident pseudo-labels.

Contribution

The work proposes a confidence-aware pseudo-labeling strategy that utilizes query data during inference to enhance segmentation performance in 3D few-shot medical imaging tasks.

Findings

Significant performance boost across multiple datasets.

Effective utilization of query information improves segmentation accuracy.

Method outperforms existing few-shot segmentation approaches.

Abstract

In recent years, few-shot segmentation (FSS) models have emerged as a promising approach in medical imaging analysis, offering remarkable adaptability to segment novel classes with limited annotated data. Existing approaches to few-shot segmentation have often overlooked the potential of the query itself, failing to fully utilize the valuable information it contains. However, treating the query as unlabeled data provides an opportunity to enhance prediction accuracy. Specifically in the domain of medical imaging, the volumetric structure of queries offers a considerable source of valuable information that can be used to improve the target slice segmentation. In this work, we present a novel strategy to efficiently leverage the intrinsic information of the query sample for final segmentation during inference. First, we use the support slices from a reference volume to generate an initial segmentation score for the query slices through a prototypical approach. Subsequently, we apply a confidence-aware pseudo-labeling procedure to transfer the most informative parts of query slices to the support set. The final prediction is performed based on the new expanded support set, enabling the prediction of a more accurate segmentation mask for the query volume. Extensive experiments show that the proposed method can effectively boost performance across diverse settings and datasets.