paper-with-me

Papers

MultiTask-CenterNet (MCN): Efficient and Diverse Multitask Learning using an Anchor Free Approach

2021-08-11 · Falk Heuer, Sven Mantowsky, Syed Saqib Bukhari, Georg Schneider

Multitask learning is a common approach in machine learning, which allows to train multiple objectives with a shared architecture. It has been shown that by training multiple tasks together inference time and compute resources can be saved, while the objectives performance remains on a similar or even higher level. However, in perception related multitask networks only closely related tasks can be found, such as object detection, instance and semantic segmentation or depth estimation. Multitask networks with diverse tasks and their effects with respect to efficiency on one another are not well studied. In this paper we augment the CenterNet anchor-free approach for training multiple diverse perception related tasks together, including the task of object detection and semantic segmentation as well as human pose estimation. We refer to this DNN as Multitask-CenterNet (MCN). Additionally, we study different MCN settings for efficiency. The MCN can perform several tasks at once while maintaining, and in some cases even exceeding, the performance values of its corresponding single task networks. More importantly, the MCN architecture decreases inference time and reduces network size when compared to a composition of single task networks.

📄 PDF Abstract BibTeX arXiv:2108.05060

Code (0)

등록된 구현이 없습니다.

Tasks

Depth Estimationobject-detectionObject DetectionPose EstimationSemantic Segmentation

Methods 이 논문이 사용한 방법론

DLA 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Batch Normalization 설명 없음
Cascade Corner Pooling Cascade Corner Pooling is a pooling layer for object detection that builds upon the corner pooling operation. Corners are…
Center Pooling Center Pooling is a pooling technique for object detection that aims to capture richer and more recognizable visual patterns. The geometric centers of objects do not…
CenterNet CenterNet is a one-stage object detector that detects each object as a triplet, rather than a pair, of keypoints. It utilizes two customized modules named [cascade corner…

Similar Papers 제목 키워드 기반

CenterNet3D: An Anchor Free Object Detector for Point Cloud

2020-07-13 · Guojun Wang, Jian Wu, Bin Tian, Siyu Teng 외

Accurate and fast 3D object detection from point clouds is a key task in autonomous driving. Existing one-stage 3D object detection methods can achieve real-time performance, however, they are dominated by anchor-based d…

3D Object DetectionAutonomous DrivingKeypoint EstimationObject+2

FII-CenterNet: An Anchor-Free Detector With Foreground Attention for Traffic Object Detection

2021-01-08 · IEEE Transactions on Vehicular Technology 2021 1 · Siqi Fan, Fenghua Zhu, Shichao Chen, HUI ZHANG 외

Most successful object detectors are anchor-based, which is difficult to adapt to the diversity of traffic objects. In this paper, we propose a novel anchor-free method, called FII-CenterNet, which introduces the foregro…

Diversityobject-detectionObject DetectionRegion Proposal+2

ProAI: An Efficient Embedded AI Hardware for Automotive Applications -- a Benchmark Study

2021-08-11 · Sven Mantowsky, Falk Heuer, Syed Saqib Bukhari, Michael Keckeisen 외

Development in the field of Single Board Computers (SBC) have been increasing for several years. They provide a good balance between computing performance and power consumption which is usually required for mobile platfo…

Autonomous DrivingCPUGPU

Representation Learning Enables Scalable Multitask Deep Reinforcement Learning

2026-06-04 · Johan Obando-Ceron, Lu Li, Scott Fujimoto, Pierre-Luc Bacon 외 arxiv

Scaling reinforcement learning (RL) to diverse multitask settings remains a central challenge. While recent advances in model-based RL achieve strong performance, they rely on planning and complex training pipelines, mak…

Representation LearningReinforcement LearningContinuous Control

CenterNet++ for Object Detection

2022-04-18 · Kaiwen Duan, Song Bai, Lingxi Xie, Honggang Qi 외

There are two mainstreams for object detection: top-down and bottom-up. The state-of-the-art approaches mostly belong to the first category. In this paper, we demonstrate that the bottom-up approaches are as competitive …

Objectobject-detectionObject DetectionTriplet