Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation

TL;DR

This paper introduces a dynamic prototype convolution network (DPCN) that enhances few-shot semantic segmentation by capturing intrinsic object details through dynamic kernels and enriched context modules, outperforming existing methods.

Contribution

The paper proposes a novel DPCN with dynamic convolution, support activation, and feature filtering modules for improved detail capture in few-shot segmentation.

Findings

DPCN achieves superior accuracy on PASCAL-5i and COCO-20i datasets.

DPCN performs well in both 1-shot and 5-shot settings.

The method effectively captures object details like holes and slots.

Abstract

The key challenge for few-shot semantic segmentation (FSS) is how to tailor a desirable interaction among support and query features and/or their prototypes, under the episodic training scenario. Most existing FSS methods implement such support-query interactions by solely leveraging plain operations - e.g., cosine similarity and feature concatenation - for segmenting the query objects. However, these interaction approaches usually cannot well capture the intrinsic object details in the query images that are widely encountered in FSS, e.g., if the query object to be segmented has holes and slots, inaccurate segmentation almost always happens. To this end, we propose a dynamic prototype convolution network (DPCN) to fully capture the aforementioned intrinsic details for accurate FSS. Specifically, in DPCN, a dynamic convolution module (DCM) is firstly proposed to generate dynamic kernels from support foreground, then information interaction is achieved by convolution operations over query features using these kernels. Moreover, we equip DPCN with a support activation module (SAM) and a feature filtering module (FFM) to generate pseudo mask and filter out background information for the query images, respectively. SAM and FFM together can mine enriched context information from the query features. Our DPCN is also flexible and efficient under the k-shot FSS setting. Extensive experiments on PASCAL-5i and COCO-20i show that DPCN yields superior performances under both 1-shot and 5-shot settings.