Multi-task deep learning for medical image computing and analysis: A review
The renaissance of deep learning has provided promising solutions to various tasks. While
conventional deep learning models are constructed for a single specific task, multi-task deep …
conventional deep learning models are constructed for a single specific task, multi-task deep …
Advances and challenges in meta-learning: A technical review
A Vettoruzzo, MR Bouguelia… - … on Pattern Analysis …, 2024 - ieeexplore.ieee.org
Meta-learning empowers learning systems with the ability to acquire knowledge from
multiple tasks, enabling faster adaptation and generalization to new tasks. This review …
multiple tasks, enabling faster adaptation and generalization to new tasks. This review …
Bevformer: Learning bird's-eye-view representation from multi-camera images via spatiotemporal transformers
Abstract 3D visual perception tasks, including 3D detection and map segmentation based on
multi-camera images, are essential for autonomous driving systems. In this work, we present …
multi-camera images, are essential for autonomous driving systems. In this work, we present …
Petrv2: A unified framework for 3d perception from multi-camera images
In this paper, we propose PETRv2, a unified framework for 3D perception from multi-view
images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which …
images. Based on PETR, PETRv2 explores the effectiveness of temporal modeling, which …
Sam-clip: Merging vision foundation models towards semantic and spatial understanding
The landscape of publicly available vision foundation models (VFMs) such as CLIP and
SAM is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their …
SAM is expanding rapidly. VFMs are endowed with distinct capabilities stemming from their …
Ties-merging: Resolving interference when merging models
Transfer learning–ie, further fine-tuning a pre-trained model on a downstream task–can
confer significant advantages, including improved downstream performance, faster …
confer significant advantages, including improved downstream performance, faster …
MBEV: Multi-Camera Joint 3D Detection and Segmentation with Unified Birds-Eye View Representation
In this paper, we propose M $^ 2$ BEV, a unified framework that jointly performs 3D object
detection and map segmentation in the Birds Eye View~(BEV) space with multi-camera …
detection and map segmentation in the Birds Eye View~(BEV) space with multi-camera …
Ext5: Towards extreme multi-task scaling for transfer learning
Despite the recent success of multi-task learning and transfer learning for natural language
processing (NLP), few works have systematically studied the effect of scaling up the number …
processing (NLP), few works have systematically studied the effect of scaling up the number …
Do current multi-task optimization methods in deep learning even help?
D Xin, B Ghorbani, J Gilmer… - Advances in neural …, 2022 - proceedings.neurips.cc
Recent research has proposed a series of specialized optimization algorithms for deep multi-
task models. It is often claimed that these multi-task optimization (MTO) methods yield …
task models. It is often claimed that these multi-task optimization (MTO) methods yield …
Real-world image super-resolution as multi-task learning
In this paper, we take a new look at real-world image super-resolution (real-SR) from a multi-
task learning perspective. We demonstrate that the conventional formulation of real-SR can …
task learning perspective. We demonstrate that the conventional formulation of real-SR can …