Efficient semantic image segmentation with superpixel pooling

Abstract

In this work, we evaluate the use of superpixel pooling layers in deep network architectures for semantic segmentation. Superpixel pooling is a flexible and efficient replacement for other pooling strategies that incorporates spatial prior information. We propose a simple and efficient GPU-implementation of the layer and explore several designs for the integration of the layer into existing network architectures. We provide experimental results on the IBSR and Cityscapes dataset, demonstrating that superpixel pooling can be leveraged to consistently increase network accuracy with minimal computational overhead. Source code is available at https://github.com/bermanmaxim/superpixPool

References in corpus (4)

• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Superpixels: An Evaluation of the State-of-the-Art
• gSLICr: SLIC superpixels at over 250Hz

Cited by in corpus (4)

• OccuSeg: Occupancy-aware 3D Instance Segmentation
• Recognizing Image Objects by Relational Analysis Using Heterogeneous Superpixels and Deep Convolutional Features
• Generating superpixels using deep image representations
• Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder