[ACM MM 2024] AdapMTL: 多任务学习模型的自适应剪枝框架

AdapMTL: Adaptive Pruning Framework for Multitask Learning Model

AdapMTL: Adaptive Pruning Framework for Multitask Learning Model (arxiv.org)

Abstract

In the domain of multimedia and multimodal processing, the efficient handling of diverse data streams such as images, video, and sensor data is paramount. Model compression and multitask learning (MTL) are crucial in this field, offering the potential to address the resource-intensive demands of processing and interpreting multiple forms of media simultaneously. However, effectively compressing a multitask model presents significant challenges due to the complexiti