Imagen de Portada

A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track

Guardado en:
Publicado en:arXiv.org (Feb 27, 2024), p. n/a
Autor principal: Chen, Zehui
Otros Autores: Wang, Qiuchen, Li, Zhenyu, Liu, Jiaming, Zhang, Shanghang, Zhao, Feng
Publicado:
Cornell University Library, arXiv.org
Materias:
Visual tasks
Instance segmentation
Robustness (mathematics)
Visual perception
Learning
Object recognition
Visual perception driven algorithms
Acceso en línea:Citation/Abstract
Full text outside of ProQuest
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Resumen:In this report, we present our solution to the multi-task robustness track of the 1st Visual Continual Learning (VCL) Challenge at ICCV 2023 Workshop. We propose a vanilla framework named UniNet that seamlessly combines various visual perception algorithms into a multi-task model. Specifically, we choose DETR3D, Mask2Former, and BinsFormer for 3D object detection, instance segmentation, and depth estimation tasks, respectively. The final submission is a single model with InternImage-L backbone, and achieves a 49.6 overall score (29.5 Det mAP, 80.3 mTPS, 46.4 Seg mAP, and 7.93 silog) on SHIFT validation set. Besides, we provide some interesting observations in our experiments which may facilitate the development of multi-task learning in dense visual prediction.
ISSN:2331-8422
Fuente:Engineering Database