A Key to Effective Multi-task Learning: Separate Query Selection for Task-Synergized Handling and Node Utilization
Shan-Ya Yang, Hao-Chung Cheng, Chien-Yao Wang, Jia-Ching Wang, Chun-Yi Lee
Abstract
In the realm of computer vision, effectively handling multi-tasks simultaneously presents a challenge that necessitates innovative solutions. To better address multiple vision problems, we introduce SeTano, an integrated Graph Neural Network (GNN)-based framework. This framework comprises a Dynamic Edge-Sensing GNN (DES-GNN) backbone, which can dynamically adjust edges to extract more pivotal features, and a downstream design which includes a node reduction and a separate query selection strategy. To validate our approach, we perform multi-task experiments on the ImageNet and MS COCO datasets. The results indicate that the integrated design of SeTano leads to enhanced performance in various vision multi-tasks.
BibTeX
@inproceedings{icassp2025_akeytoeffectivem,
title = {A Key to Effective Multi-task Learning: Separate Query Selection for Task-Synergized Handling and Node Utilization},
author = {Shan-Ya Yang and Hao-Chung Cheng and Chien-Yao Wang and Jia-Ching Wang and Chun-Yi Lee},
booktitle = {ICASSP 2025},
year = {2025}
}