keyword

image cascade network

An image cascade network is a deep convolutional neural network architecture designed for real-time semantic segmentation of high-resolution images by balancing computational efficiency with segmentation accuracy. It processes multiple downsampled versions of an input image across a multi-branch, cascaded structure. In this setup, low-resolution inputs pass through deeper subnetworks to efficiently capture high-level semantic context, while higher-resolution inputs pass through shallower subnetworks to preserve spatial and boundary details with minimal computational overhead. The resulting multi-scale feature maps are progressively integrated using cascade feature fusion mechanisms and refined under intermediate label guidance to produce accurate, pixel-level predictions at high processing speeds.

1 item

ICNet for Real-Time Semantic Segmentation on High-Resolution Images

Hengshuang Zhao, Xiaojuan Qi, Xiaoyong Shen, Jianping Shi, Jiaya Jia

OrganizationsSenseTimeTencentThe Chinese University of Hong Kong

Why you should read this

Introduces an image cascade network that combines multi-resolution branches with cascade feature fusion to deliver real-time, high-accuracy semantic segmentation on high-resolution images.

We focus on the challenging task of real-time semantic segmentation in this paper. It finds many practical applications and yet is with fundamental difficulty of reducing a large portion of computation for pixel-wise label inference. We propose an image cascade network (ICNet) that incorporates multi-resolution branches under proper label guidance to address this challenge. We provide in-depth analysis of our framework and introduce the cascade feature fusion unit to quickly achieve high-quality segmentation. Our system yields real-time inference on a single GPU card with decent quality results evaluated on challenging datasets like Cityscapes, CamVid and COCO-Stuff.

Source

https://link.springer.com/content/pdf/10.1007/978-3-030-01219-9_25.pdf

Added

2026-09-24