YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception (2022-08-24T00:00:00.000000Z)

TL;DR

This paper proposed an effective and efficient multi-task learning network to simultaneously perform the task of traffic object detection, drivable road area segmentation and lane detection and achieved the new state-of-the-art SOTA performance in terms of accuracy and speed on the challenging BDD100K dataset.

Abstract

Over the last decade, multi-tasking learning approaches have achieved promising results in solving panoptic driving perception problems, providing both high-precision and high-efficiency performance. It has become a popular paradigm when designing networks for real-time practical autonomous driving system, where computation resources are limited. This paper proposed an effective and efficient multi-task learning network to simultaneously perform the task of traffic object detection, drivable road area segmentation and lane detection. Our model achieved the new state-of-the-art (SOTA) performance in terms of accuracy and speed on the challenging BDD100K dataset. Especially, the inference time is reduced by half compared to the previous SOTA model. Code will be released in the near future.

Authors

Qichao Zhao

1 papers

Shuyi Zhang

1 papers

Yinzi Chen

1 papers

TL;DR

Abstract

Authors

References30 items

YOLOv7: Trainable Bag-of-Freebies Sets New State-of-the-Art for Real-Time Object Detectors

HybridNets: End-to-End Perception Network

YOLOP: You Only Look Once for Panoptic Driving Perception

YOLOX: Exceeding YOLO Series in 2021

You Only Learn One Representation: Unified Network for Multiple Tasks

Location-Sensitive Visual Recognition with Cross-IOU Loss

Scaled-YOLOv4: Scaling Cross Stage Partial Network

DLT-Net: Joint Detection of Drivable Areas, Lane Lines, and Traffic Objects

Improved Mosaic: Algorithms for more Complex Images

UNet 3+: A Full-Scale Connected UNet for Medical Image Segmentation

Learning Lightweight Lane Detection CNNs by Self Attention Distillation

CenterNet: Keypoint Triplets for Object Detection

AnatomyNet: Deep learning for fast and fully automated whole‐volume segmentation of head and neck anatomy

LaneNet: Real-Time Lane Detection Networks for Autonomous Driving

BDD100K: A Diverse Driving Video Database with Scalable Annotation Tooling

YOLOv3: An Incremental Improvement

Path Aggregation Network for Instance Segmentation

mixup: Beyond Empirical Risk Minimization

SCNN: An accelerator for compressed-sparse convolutional neural networks

YOLO9000: Better, Faster, Stronger

MultiNet: Real-time Joint Semantic Reasoning for Autonomous Driving

Feature Pyramid Networks for Object Detection

Pyramid Scene Parsing Network

SGDR: Stochastic Gradient Descent with Warm Restarts

R-FCN: Object Detection via Region-based Fully Convolutional Networks

Deep Residual Learning for Image Recognition

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

Kaiming He, and Jian Sun. R-fcn: Object detection via region-based fully convolutional networks. Advances in neural information processing systems

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names