Prior Guided Feature Enrichment Network for Few-Shot Segmentation

TL;DR

PFENet introduces a novel prior-guided feature enrichment approach for few-shot segmentation, significantly enhancing generalization and spatial consistency, outperforming existing methods on standard benchmarks.

Contribution

The paper proposes a training-free prior mask generation and a feature enrichment module, improving few-shot segmentation performance and generalization without additional training.

Findings

Outperforms state-of-the-art methods on PASCAL-5i and COCO datasets.

Improves baseline performance with novel prior and feature enrichment techniques.

Generalizes to cases without labeled support samples.

Abstract

State-of-the-art semantic segmentation methods require sufficient labeled data to achieve good results and hardly work on unseen classes without fine-tuning. Few-shot segmentation is thus proposed to tackle this problem by learning a model that quickly adapts to new classes with a few labeled support samples. Theses frameworks still face the challenge of generalization ability reduction on unseen classes due to inappropriate use of high-level semantic information of training classes and spatial inconsistency between query and support targets. To alleviate these issues, we propose the Prior Guided Feature Enrichment Network (PFENet). It consists of novel designs of (1) a training-free prior mask generation method that not only retains generalization power but also improves model performance and (2) Feature Enrichment Module (FEM) that overcomes spatial inconsistency by adaptively enriching query features with support features and prior masks. Extensive experiments on PASCAL-5$^i$ and COCO prove that the proposed prior generation method and FEM both improve the baseline method significantly. Our PFENet also outperforms state-of-the-art methods by a large margin without efficiency loss. It is surprising that our model even generalizes to cases without labeled support samples. Our code is available at https://github.com/Jia-Research-Lab/PFENet/.