A Caltech Library Service

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

Xiao, Junfei and Xu, Zhichao and Lan, Shiyi and Yu, Zhiding and Yuille, Alan and Anandkumar, Anima (2022) 1st Place Solution of The Robust Vision Challenge 2022 Semantic Segmentation Track. . (Unpublished)

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item:


This report describes the winning solution to the Robust Vision Challenge (RVC) semantic segmentation track at 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 can serve as a strong baseline for the multi-domain segmentation task and benefit future works. Code will be available at

Item Type:Report or Paper (Discussion Paper)
Related URLs:
URLURL TypeDescription Paper
Xu, Zhichao0000-0002-9369-2944
Yuille, Alan0000-0001-5207-9249
Anandkumar, Anima0000-0002-6974-6797
Record Number:CaltechAUTHORS:20221221-004714993
Persistent URL:
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:118554
Deposited By: George Porter
Deposited On:22 Dec 2022 18:39
Last Modified:22 Dec 2022 18:39

Repository Staff Only: item control page