Progressively Dual Prior Guided Few-shot Semantic Segmentation

TL;DR

This paper introduces a novel few-shot semantic segmentation network that uses dual prior masks and progressive detail enrichment to improve segmentation accuracy, especially in complex scenes with large appearance variance.

Contribution

It proposes a dual prior mask generation module and a progressive semantic detail enrichment module for better background suppression and detail capture in few-shot segmentation.

Findings

Achieves state-of-the-art performance on PASCAL-5i and MS COCO datasets.

Effectively suppresses background activation and captures semantic details.

Demonstrates robustness in scenes with large object appearance variance.

Abstract

Few-shot semantic segmentation task aims at performing segmentation in query images with a few annotated support samples. Currently, few-shot segmentation methods mainly focus on leveraging foreground information without fully utilizing the rich background information, which could result in wrong activation of foreground-like background regions with the inadaptability to dramatic scene changes of support-query image pairs. Meanwhile, the lack of detail mining mechanism could cause coarse parsing results without some semantic components or edge areas since prototypes have limited ability to cope with large object appearance variance. To tackle these problems, we propose a progressively dual prior guided few-shot semantic segmentation network. Specifically, a dual prior mask generation (DPMG) module is firstly designed to suppress the wrong activation in foreground-background comparison manner by regarding background as assisted refinement information. With dual prior masks refining the location of foreground area, we further propose a progressive semantic detail enrichment (PSDE) module which forces the parsing model to capture the hidden semantic details by iteratively erasing the high-confidence foreground region and activating details in the rest region with a hierarchical structure. The collaboration of DPMG and PSDE formulates a novel few-shot segmentation network that can be learned in an end-to-end manner. Comprehensive experiments on PASCAL-5i and MS COCO powerfully demonstrate that our proposed algorithm achieves the great performance.