Radar as a Teacher: Weakly Supervised Vehicle Detection using Radar Labels

Chadwick, Simon; Newman, Paul

doi:10.1109/icra40945.2020.9196855

Cited by 9 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most importantly, no existing study has hardly leveraged RGB to TIR translation to train to tasks with extreme level of difficulty in manual labeling. Using our translation network, we not only enabled supervised learning on tasks with challenging labels such as deep optical flow estimation in TIR, but inspired by [15], we also validated the effectiveness of our proposed method in object detection without the need for any manual annotations.…”

Section: Introductionmentioning

confidence: 86%

Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels

Lee¹,

Jeon²,

Cho³

et al. 2023

Preprint

View full text Add to dashboard Cite

The insufficient number of annotated thermal infrared (TIR) image datasets not only hinders TIR imagebased deep learning networks to have comparable performances to that of RGB but it also limits the supervised learning of TIR image-based tasks with challenging labels. As a remedy, we propose a modified multidomain RGB to TIR image translation model focused on edge preservation to employ annotated RGB images with challenging labels. Our proposed method not only preserves key details in the original image but also leverages the optimal TIR style code to portray accurate TIR characteristics in the translated image, when applied on both synthetic and real world RGB images. Using our translation model, we have enabled the supervised learning of deep TIR image-based optical flow estimation and object detection that ameliorated in deep TIR optical flow estimation by reduction in end point error by 56.5% on average and the best object detection mAP of 23.9% respectively. Our code and supplementary materials are available at https://github.com/rpmsnu/sRGB-TIR.

show abstract

Section: Introductionmentioning

confidence: 86%

Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels

Lee¹,

Jeon²,

Cho³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A straightforward solution for reducing annotation efforts for vehicle detection is to train a detector from weak annotations. Chadwick et al [34] used a radar to automatically generate noisy labels and clean these labels to give good detector performance without the need for hand labeling. Another solution is based on semi-supervised learning [35,36], whereby the annotations for some images are avoided.…”

Section: Vehicle Detection Methodsmentioning

confidence: 99%

Select Informative Samples for Night-Time Vehicle Detection Benchmark in Urban Scenes

Wang,

Tu,

Al-Hassani

et al. 2023

Remote Sensing

View full text Add to dashboard Cite

Night-time vehicle detection plays a vital role due to the high incidence of abnormal events in our daily security field. However, existing studies mainly focus on vehicle detection in autonomous driving and traffic intersection scenes, but ignore urban scenes. There are vast differences between these scenes, such as viewpoint, position, illumination, etc. In this paper, the authors present a night-time vehicle detection dataset collected from urban scenes, named Vehicle Detection in Night-Time Urban Scene (VD-NUS). The VD-NUS dataset consists of more than 100 K challenging images, comprising a total of about 500 K labelled vehicles. This paper introduces a vehicle detection framework via an active auxiliary mechanism (AAM) to reduce the annotation workload. The proposed AAM framework can actively select the informative sample for annotation by estimating its uncertainty and locational instability. Furthermore, this paper proposes a computer-assisted detection module embedded in the AAM framework to help human annotators to rapidly and accurately label the selected data. AAM outperformed the baseline method (random sampling) by up to 0.91 AP and 3.0 MR−2 on the VD-NUS dataset.

show abstract

“…In a weakly-supervised setting, τ is unknown and one must either estimate it or try different schedules. Although it has traditionally been used in classification tasks, Co-Teaching has also recently seen some success when training an object detector from noisy bounding boxes [5]. To the best of our knowledge, this work is the first to adapt it to a segmentation task.…”

Section: Co-teaching For Segmentationmentioning

confidence: 99%

Weakly-Supervised Free Space Estimation through Stochastic Co-Teaching

Robinet

Parera

Hundt³

et al. 2022

2022 IEEE/CVF Winter Conference on Applications of Computer Vision Workshops (WACVW)

View full text Add to dashboard Cite

Free space estimation is an important problem for autonomous robot navigation. Traditional camera-based approaches train a segmentation model using an annotated dataset. The training data needs to capture the wide variety of environments and weather conditions encountered at runtime, making the annotation cost prohibitively high. In this work, we propose a novel approach for obtaining free space estimates from images taken with a single roadfacing camera. We rely on a technique that generates weak free space labels without any supervision, which are then used as ground truth to train a segmentation model for free space estimation. Our work differs from prior attempts by explicitly taking label noise into account through the use of Co-Teaching. Since Co-Teaching has traditionally been investigated in classification tasks, we adapt it for segmentation and examine how its parameters affect performances in our experiments. In addition, we propose Stochastic Co-Teaching, which is a novel method to select clean samples that leads to enhanced results. We achieve an IoU of 82.6%, a Precision of 90.9%, and a Recall of 90.3%. Our best model reaches 87% of the IoU, 93% of the Precision, and 93% of the Recall of the equivalent fully-supervised baseline while using no human annotations. To the best of our knowledge, this work is the first to use Co-Teaching to train a free space segmentation model under explicit label noise. Our implementation and models are freely available online.

show abstract

Radar as a Teacher: Weakly Supervised Vehicle Detection using Radar Labels

Cited by 9 publications

References 20 publications

Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels

Edge-guided Multi-domain RGB-to-TIR image Translation for Training Vision Tasks with Challenging Labels

Select Informative Samples for Night-Time Vehicle Detection Benchmark in Urban Scenes

Weakly-Supervised Free Space Estimation through Stochastic Co-Teaching

Contact Info

Product

Resources

About