CVMay 11, 2018

ContextNet: Exploring Context and Detail for Semantic Segmentation in Real-time

arXiv:1805.04554v4255 citations
Originality Incremental advance
AI Analysis

This addresses the need for efficient semantic segmentation in real-time applications like autonomous driving, though it is incremental as it builds on existing techniques like factorized convolution.

The paper tackles the problem of achieving real-time semantic segmentation with low computational cost while maintaining accuracy, proposing ContextNet which achieves 66.1% accuracy at 18.3 fps on the Cityscapes dataset.

Modern deep learning architectures produce highly accurate results on many challenging semantic segmentation datasets. State-of-the-art methods are, however, not directly transferable to real-time applications or embedded devices, since naive adaptation of such systems to reduce computational cost (speed, memory and energy) causes a significant drop in accuracy. We propose ContextNet, a new deep neural network architecture which builds on factorized convolution, network compression and pyramid representation to produce competitive semantic segmentation in real-time with low memory requirement. ContextNet combines a deep network branch at low resolution that captures global context information efficiently with a shallow branch that focuses on high-resolution segmentation details. We analyse our network in a thorough ablation study and present results on the Cityscapes dataset, achieving 66.1% accuracy at 18.3 frames per second at full (1024x2048) resolution (41.9 fps with pipelined computations for streamed data).

Code Implementations2 repos
Foundations

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

Your Notes