SimPropNet: Improved Similarity Propagation for Few-shot Image Segmentation
This work addresses the challenge of segmenting objects with limited labeled data, which is incremental as it builds on existing deep learning approaches for few-shot segmentation.
The paper tackles the problem of few-shot image segmentation by identifying gaps in existing similarity propagation methods and proposes SimPropNet to improve similarity utilization, achieving state-of-the-art results on the PASCAL-5i dataset for one-shot and five-shot segmentation.
Few-shot segmentation (FSS) methods perform image segmentation for a particular object class in a target (query) image, using a small set of (support) image-mask pairs. Recent deep neural network based FSS methods leverage high-dimensional feature similarity between the foreground features of the support images and the query image features. In this work, we demonstrate gaps in the utilization of this similarity information in existing methods, and present a framework - SimPropNet, to bridge those gaps. We propose to jointly predict the support and query masks to force the support features to share characteristics with the query features. We also propose to utilize similarities in the background regions of the query and support images using a novel foreground-background attentive fusion mechanism. Our method achieves state-of-the-art results for one-shot and five-shot segmentation on the PASCAL-5i dataset. The paper includes detailed analysis and ablation studies for the proposed improvements and quantitative comparisons with contemporary methods.