paper-with-me

홈 › Papers

Optimizing Anchor-based Detectors for Autonomous Driving Scenes

2022-08-11 · Xianzhi Du, Wei-Chih Hung, Tsung-Yi Lin

This paper summarizes model improvements and inference-time optimizations for the popular anchor-based detectors in the scenes of autonomous driving. Based on the high-performing RCNN-RS and RetinaNet-RS detection frameworks designed for common detection scenes, we study a set of framework improvements to adapt the detectors to better detect small objects in crowd scenes. Then, we propose a model scaling strategy by scaling input resolution and model size to achieve a better speed-accuracy trade-off curve. We evaluate our family of models on the real-time 2D detection track of the Waymo Open Dataset (WOD). Within the 70 ms/frame latency constraint on a V100 GPU, our largest Cascade RCNN-RS model achieves 76.9% AP/L1 and 70.1% AP/L2, attaining the new state-of-the-art on WOD real-time 2D detection. Our fastest RetinaNet-RS model achieves 6.3 ms/frame while maintaining a reasonable detection precision at 50.7% AP/L1 and 42.9% AP/L2.

📄 PDF Abstract BibTeX arXiv:2208.06062

Code (0)

등록된 구현이 없습니다.

Tasks

Autonomous DrivingGPU

Methods 이 논문이 사용한 방법론

ReLU How Do I Communicate to Expedia? How Do I Communicate to Expedia? – Call ☎️ +1-(888) 829 (0881) or +1-805-330-4056 or +1-805-330-4056 for Live Support & Special Travel…
Max Pooling Max Pooling is a pooling operation that calculates the maximum value for patches of a feature map, and uses it to create a downsampled (pooled) feature map. It is usually…
Residual Connection 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…
Average Pooling 설명 없음
Residual Block Residual Blocks are skip-connection blocks that learn residual functions with reference to the layer inputs, instead of learning unreferenced functions. They were introduced…
Batch Normalization 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Similar Papers 제목 키워드 기반

One-Stage Object Detectors in Autonomous Driving

2026-08-19 · Jonel Roman, Ryan Sirjue, Peter Nguyen, Daniel Krutky 외 arxiv

Autonomous vehicles depend on fast and reliable perception systems to detect surrounding vehicles, pedestrians, cyclists, traffic signs, and other road objects in real time. This paper presents a comprehensive survey and…

Autonomous VehiclesAutonomous Driving

Evaluating Object (mis)Detection from a Safety and Reliability Perspective: Discussion and Measures

2022-03-04 · Andrea Ceccarelli, Leonardo Montecchi

We argue that object detectors in the safety critical domain should prioritize detection of objects that are most likely to interfere with the actions of the autonomous actor. Especially, this applies to objects that can…

Autonomous DrivingObjectobject-detectionObject Detection

CODA: A Real-World Road Corner Case Dataset for Object Detection in Autonomous Driving

2022-03-15 · Kaican Li, Kai Chen, Haoyu Wang, Lanqing Hong 외

Contemporary deep-learning object detection methods for autonomous driving usually assume prefixed categories of common traffic participants, such as pedestrians and cars. Most existing detectors are unable to detect unc…

Autonomous DrivingObjectobject-detectionObject Detection

Enhancing Object Detection for Autonomous Driving by Optimizing Anchor Generation and Addressing Class Imbalance

2021-04-08 · Manuel Carranza-García, Pedro Lara-Benítez, Jorge García-Gutiérrez, José C. Riquelme

Object detection has been one of the most active topics in computer vision for the past years. Recent works have mainly focused on pushing the state-of-the-art in the general-purpose COCO benchmark. However, the use of s…

Autonomous DrivingAutonomous VehiclesEvolutionary Algorithmsobject-detection+1

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