Dilated SpineNet for Semantic Segmentation

03/23/2021
by   Abdullah Rashwan, et al.
0

Scale-permuted networks have shown promising results on object bounding box detection and instance segmentation. Scale permutation and cross-scale fusion of features enable the network to capture multi-scale semantics while preserving spatial resolution. In this work, we evaluate this meta-architecture design on semantic segmentation - another vision task that benefits from high spatial resolution and multi-scale feature fusion at different network stages. By further leveraging dilated convolution operations, we propose SpineNet-Seg, a network discovered by NAS that is searched from the DeepLabv3 system. SpineNet-Seg is designed with a better scale-permuted network topology with customized dilation ratios per block on a semantic segmentation task. SpineNet-Seg models outperform the DeepLabv3/v3+ baselines at all model scales on multiple popular benchmarks in speed and accuracy. In particular, our SpineNet-S143+ model achieves the new state-of-the-art on the popular Cityscapes benchmark at 83.04 PASCAL VOC2012 benchmark at 85.56 promising results on a challenging Street View segmentation dataset. Code and checkpoints will be open-sourced.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 7

03/01/2022

Boundary Corrected Multi-scale Fusion Network for Real-time Semantic Segmentation

Image semantic segmentation aims at the pixel-level classification of im...
03/26/2022

Feature Selective Transformer for Semantic Image Segmentation

Recently, it has attracted more and more attentions to fuse multi-scale ...
03/23/2022

Revisiting Multi-Scale Feature Fusion for Semantic Segmentation

It is commonly believed that high internal resolution combined with expe...
06/08/2021

SpaceMeshLab: Spatial Context Memoization and Meshgrid Atrous Convolution Consensus for Semantic Segmentation

Semantic segmentation networks adopt transfer learning from image classi...
03/25/2022

Multi-scale and Cross-scale Contrastive Learning for Semantic Segmentation

This work considers supervised contrastive learning for semantic segment...
09/02/2020

Multi-domain semantic segmentation with pyramidal fusion

We present our submission to the semantic segmentation contest of the Ro...
08/23/2020

Robust Vision Challenge 2020 – 1st Place Report for Panoptic Segmentation

In this technical report, we present key details of our winning panoptic...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.