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

Zehui Chen, Qiuchen Wang, Zhenyu Li, Jiaming Liu, Shanghang Zhang +1 more
2/27/2024
cs.CV

No confident code implementation found for this paper. 1 possible match can be shown below.

Abstract

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.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. 1 weaker match is hidden by default — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Multi-task View Synthesis with Neural Radiance Fields

85% match1 repo122026

3D-Aware Multi-Task Learning with Cross-View Correlations for Dense Scene Understanding

85% match2025

Optimizing Dense Visual Predictions Through Multi-Task Coherence and Prioritization

85% match1 repo22024

WHU-Synthetic: A Synthetic Perception Dataset for 3-D Multitask Model Research

84% match1 repo162024

MTLSI-Net: A Linear Semantic Interaction Network for Parameter-Efficient Multi-Task Dense Prediction

83% match2026

M2H: Multi-Task Learning with Efficient Window-Based Cross-Task Attention for Monocular Spatial Perception

83% match2025

Cite this paper

@article{chen2024vanilla,
  title  = {A Vanilla Multi-Task Framework for Dense Visual Prediction Solution to 1st VCL Challenge -- Multi-Task Robustness Track},
  author = {Zehui Chen and Qiuchen Wang and Zhenyu Li and Jiaming Liu and Shanghang Zhang and Feng Zhao},
  year   = {2024},
  eprint = {2402.17319},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2402.17319v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2402.17319.svg)](https://codeofpaper.com/paper/2402.17319)

Discussion