Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation

by   Jie Liu, et al.

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.


page 2

page 4

page 5

page 6

page 7

page 9

page 10

page 11


Multi-similarity based Hyperrelation Network for few-shot segmentation

Few-shot semantic segmentation aims at recognizing the object regions of...

Self-Calibrated Cross Attention Network for Few-Shot Segmentation

The key to the success of few-shot segmentation (FSS) lies in how to eff...

Feature Weighting and Boosting for Few-Shot Segmentation

This paper is about few-shot segmentation of foreground objects in image...

SG-One: Similarity Guidance Network for One-Shot Semantic Segmentation

One-shot semantic segmentation poses a challenging task of recognizing t...

Breaking Immutable: Information-Coupled Prototype Elaboration for Few-Shot Object Detection

Few-shot object detection, expecting detectors to detect novel classes w...

Few-Shot Segmentation via Rich Prototype Generation and Recurrent Prediction Enhancement

Prototype learning and decoder construction are the keys for few-shot se...

A Self-Distillation Embedded Supervised Affinity Attention Model for Few-Shot Segmentation

Few-shot semantic segmentation is a challenging task of predicting objec...

Please sign up or login with your details

Forgot password? Click here to reset