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 …

Meta-learning empowers learning systems with the ability to acquire knowledge from
multiple tasks, enabling faster adaptation and generalization to new tasks. This review …

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 …

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 …

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 …

Transfer learning–ie, further fine-tuning a pre-trained model on a downstream task–can
confer significant advantages, including improved downstream performance, faster …

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 …

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 …

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 …

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 …