1st Place Solution of The Robust Vision Challenge (RVC) 2022 Semantic Segmentation Track

10/23/2022
by   Junfei Xiao, et al.
20

This report describes the winning solution to the semantic segmentation task of the Robust Vision Challenge on ECCV 2022. Our method adopts the FAN-B-Hybrid model as the encoder and uses Segformer as the segmentation framework. The model is trained on a composite dataset consisting of images from 9 datasets (ADE20K, Cityscapes, Mapillary Vistas, ScanNet, VIPER, WildDash 2, IDD, BDD, and COCO) with a simple dataset balancing strategy. All the original labels are projected to a 256-class unified label space, and the model is trained using a cross-entropy loss. Without significant hyperparameter tuning or any specific loss weighting, our solution ranks the first place on all the testing semantic segmentation benchmarks from multiple domains (ADE20K, Cityscapes, Mapillary Vistas, ScanNet, VIPER, and WildDash 2). The proposed method could serve as a strong baseline for the multi-domain segmentation task and benefit future works. Code will be available at https://github.com/lambert-x/RVC_Segmentation.

READ FULL TEXT

page 1

page 2

page 3

research
06/28/2021

Striking the Right Balance: Recall Loss for Semantic Segmentation

Class imbalance is a fundamental problem in computer vision applications...
research
06/25/2023

The Second-place Solution for CVPR VISION 23 Challenge Track 1 – Data Effificient Defect Detection

The Vision Challenge Track 1 for Data-Effificient Defect Detection requi...
research
12/08/2022

An Empirical Study on Multi-Domain Robust Semantic Segmentation

How to effectively leverage the plentiful existing datasets to train a r...
research
10/11/2022

Robust Human Matting via Semantic Guidance

Automatic human matting is highly desired for many real applications. We...
research
09/02/2020

Multi-domain semantic segmentation with pyramidal fusion

We present our submission to the semantic segmentation contest of the Ro...
research
04/21/2020

Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation

We propose a novel architecture called the Multi-view Self-Constructing ...
research
12/27/2021

MSeg: A Composite Dataset for Multi-domain Semantic Segmentation

We present MSeg, a composite dataset that unifies semantic segmentation ...

Please sign up or login with your details

Forgot password? Click here to reset