MTLoRA: Low-Rank Adaptation Approach for Efficient Multi-Task Learning

A Agiza, M Neseem, S Reda - Proceedings of the IEEE/CVF …, 2024 - openaccess.thecvf.com
Adapting models pre-trained on large-scale datasets to a variety of downstream tasks is a
common strategy in deep learning. Consequently parameter-efficient fine-tuning methods …

: Looking into the Future with DINO

E Karypidis, I Kakogeorgiou, S Gidaris… - arXiv preprint arXiv …, 2024 - arxiv.org
Predicting future dynamics is crucial for applications like autonomous driving and robotics,
where understanding the environment is key. Existing pixel-level methods are …

Swiss Army Knife: Synergizing Biases in Knowledge from Vision Foundation Models for Multi-Task Learning

Y Lu, S Cao, YX Wang - arXiv preprint arXiv:2410.14633, 2024 - arxiv.org
Vision Foundation Models (VFMs) have demonstrated outstanding performance on
numerous downstream tasks. However, due to their inherent representation biases …

Cross-Modal Supervision Based Road Segmentation and Trajectory Prediction with Automotive Radar

Z Wang, Y Jin, A Deligiannis… - IEEE Robotics and …, 2024 - ieeexplore.ieee.org
Automotive radar plays a crucial role in providing reliable environmental perception for
autonomous driving, particularly in challenging conditions such as high speeds and bad …

Improving Multiple Dense Prediction Performances by Exploiting Inter-Task Synergies for Neuromorphic Vision Sensors

T Zhang, Z Li, J Su, J Fang - IEEE Sensors Journal, 2024 - ieeexplore.ieee.org
Recent years have witnessed neuromorphic vision sensor (NVS) driving the performance of
dense prediction in the domain of visual perception thanks to its unique properties. Although …

Loop Improvement: An Efficient Approach for Extracting Shared Features from Heterogeneous Data without Central Server

F Li, CK Loo, WS Liew, X Liu - arXiv preprint arXiv:2403.14371, 2024 - arxiv.org
In federated learning, data heterogeneity significantly impacts performance. A typical
solution involves segregating these parameters into shared and personalized components …

Multi-Task Neural Network Mapping onto Analog-Digital Heterogeneous Accelerators

H Benmeziane, C Lammie, A Vasilopoulos… - … Learning with new …, 2024 - openreview.net
Multi-task Learning (MTL) models are increasingly popular for their ability to perform multiple
tasks using shared parameters, significantly reducing redundant computations and resource …