DeepAI AI Chat
Log In Sign Up

DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation

04/03/2019
by   Hanchao Li, et al.
Megvii Technology Limited
0

This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints. Our proposed network starts from a single lightweight backbone and aggregates discriminative features through sub-network and sub-stage cascade respectively. Based on the multi-scale feature propagation, DFANet substantially reduces the number of parameters, but still obtains sufficient receptive field and enhances the model learning ability, which strikes a balance between the speed and segmentation performance. Experiments on Cityscapes and CamVid datasets demonstrate the superior performance of DFANet with 8× less FLOPs and 2× faster than the existing state-of-the-art real-time semantic segmentation methods while providing comparable accuracy. Specifically, it achieves 70.3% Mean IOU on the Cityscapes test dataset with only 1.7 GFLOPs and a speed of 160 FPS on one NVIDIA Titan X card, and 71.3% Mean IOU with 3.4 GFLOPs while inferring on a higher resolution image.

READ FULL TEXT

page 4

page 7

08/02/2018

BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation

Semantic segmentation requires both rich spatial information and sizeabl...
04/05/2017

Not All Pixels Are Equal: Difficulty-aware Semantic Segmentation via Deep Layer Cascade

We propose a novel deep layer cascade (LC) method to improve the accurac...
09/18/2019

Feature Pyramid Encoding Network for Real-time Semantic Segmentation

Although current deep learning methods have achieved impressive results ...
12/06/2019

Waterfall Atrous Spatial Pooling Architecture for Efficient Semantic Segmentation

We propose a new efficient architecture for semantic segmentation, based...
03/23/2022

Revisiting Multi-Scale Feature Fusion for Semantic Segmentation

It is commonly believed that high internal resolution combined with expe...
10/31/2021

DRBANET: A Lightweight Dual-Resolution Network for Semantic Segmentation with Boundary Auxiliary

Due to the powerful ability to encode image details and semantics, many ...
05/22/2020

Bi-direction Context Propagation Network for Real-time Semantic Segmentation

Spatial details and context correlations are two types of critical infor...