Gaussian Dynamic Convolution for Efficient Single-Image Segmentation

Abstract

Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. In this work, we focus on the single-image segmentation problem only with some seeds such as scribbles. Inspired by the dynamic receptive field in the human being's visual system, we propose the Gaussian dynamic convolution (GDC) to fast and efficiently aggregate the contextual information for neural networks. The core idea is randomly selecting the spatial sampling area according to the Gaussian distribution offsets. Our GDC can be easily used as a module to build lightweight or complex segmentation networks. We adopt the proposed GDC to address the typical single-image segmentation tasks. Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation. Experiments demonstrate that the GDC outperforms other existing convolutions on three benchmark segmentation datasets including Pascal-Context, Pascal-VOC 2012, and Cityscapes. Additional experiments are also conducted to illustrate that the GDC can produce richer and more vivid features compared with other convolutions. In general, our GDC is conducive to the convolutional neural networks to form an overall impression of the image.

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• Interactive Medical Image Segmentation using Deep Learning with Image-specific Fine-tuning
• STC: A Simple to Complex Framework for Weakly-supervised Semantic Segmentation
• Weakly Supervised Adversarial Domain Adaptation for Semantic Segmentation in Urban Scenes
• Learning random-walk label propagation for weakly-supervised semantic segmentation
• Affinity Attention Graph Neural Network for Weakly Supervised Semantic Segmentation
• Cross-Domain Complementary Learning Using Pose for Multi-Person Part Segmentation
• Learning to Exploit the Prior Network Knowledge for Weakly-Supervised Semantic Segmentation
• Simple Does It: Weakly Supervised Instance and Semantic Segmentation

Cited by in corpus (3)

• DDistill-SR: Reparameterized Dynamic Distillation Network for Lightweight Image Super-Resolution
• Semi-supervised Semantic Segmentation for Remote Sensing Images via Multi-scale Uncertainty Consistency and Cross-Teacher-Student Attention
• PRSeg: A Lightweight Patch Rotate MLP Decoder for Semantic Segmentation