CVApr 27, 2017

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

arXiv:1704.08545v21597 citations
AI Analysis

This addresses the problem of computational efficiency for real-time semantic segmentation in applications like autonomous driving, though it is incremental as it builds on existing segmentation methods.

The paper tackles real-time semantic segmentation on high-resolution images by proposing an image cascade network (ICNet) with multi-resolution branches and cascade feature fusion, achieving real-time inference on a single GPU with decent quality results on datasets like Cityscapes, CamVid, and COCO-Stuff.

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.

Code Implementations18 repos

Data from Papers with Code (CC-BY-SA-4.0)

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes