Journal Article10.1016/j.neucom.2023.126655
YOLO*C - Adding context improves YOLO performance
18
TL;DR: This research proposes YOLO*C, a novel one-stage object detection algorithm that leverages spatial context in traffic scenes, improving performance by up to 10% in mAP.5 on BDD100K data, especially for smaller traffic objects.
read more
Abstract: You Only Look Once (YOLO) algorithms deliver state-of-the-art performance in object detection. This research proposes a novel one-stage YOLO-based algorithm that explicitly models the spatial context inherent in traffic scenes. The new YOLO*C algorithm introduces the MCTX context module and integrates loss function changes, effectively leveraging rich global context information. The performance of YOLO*C models is tested on BDD100K traffic data with multiple context variables. The results show that including context improves YOLO detection results without losing efficiency. Smaller models report the most significant improvements. The smallest model accomplished more than a 10% increase in mAP .5 compared to the baseline YOLO model. Modified YOLOv7 outperformed all models on mAP .5, including two-stage and transformer-based detectors, available at the dataset zoo. The analysis shows that improvement mainly results from better detection of smaller traffic objects, which presents a significant detection challenge within the complex traffic environment.
read more
Chat with Paper
AI Agents for this Paper
Find similar papers on Google Scholar, PubMed and Arxiv
Write a critical review of this paper
Analyze citations of this paper to find unaddressed research gaps
Citations
A Comprehensive Systematic Review of YOLO for Medical Object Detection (2018 to 2023)
Mohammed G. Ragab,Said Jadid Abdulkader,Amgad Muneer,Alawi Alqushaibi,Ebrahim Hamid Hasan Sumiea,Rizwan Qureshi,Safwan Mahmood Al-Selwi,Hitham Alhussian +7 more
TL;DR: A systematic exploration of the PubMed database to identify peer-reviewed articles published between 2018 and 2023 demonstrates the effectiveness of YOLO in outperforming alternative existing methods for medical object detection and proposes future directions for leveraging the potential of YOLO for medical object detection.
67
A YOLO-NL Object Detector for Real-time Detection
01 Oct 2023
TL;DR: This paper proposes YOLO-NL, a novel object detector that addresses limitations of YOLO models by incorporating a global dynamic label assignment strategy, CSPNet and PANet upgrades, and a Rep-CSPNet network for fast inference, achieving 52.9% mAP on COCO 2017 and 98.8% accuracy on FMD with 130 FPS.
37
Machine vision-based autonomous road hazard avoidance system for self-driving vehicles
Chengqun Qiu,Haojun Tang,Yong‐Hua Yang,Xiaochun Wan,Xixi Xu,Shengqiang Lin,Ziheng Lin,Mingyu Meng,Changli Zha +8 more
TL;DR: Optimized target detection algorithm for road hazard avoidance in self-driving vehicles using deep learning. The algorithm enhances image learning capabilities and improves small target detection accuracy. It exhibits more stable variations in vehicle control parameters and enhances the robustness of the driving system's visual avoidance functionality.
Exploring YOLOv8 Pretrain for Real-Time Detection of Indonesian Native Fish Species
TL;DR: The YOLOv8 Pretrain model is effective in detecting Indonesian native fish species in real-time with an accuracy of 89.6%.
7
Z-YOLOv8s-based approach for road object recognition in complex traffic scenarios
Ruixin Zhao,Sai Hong Tang,Eris Elianddy Supeni,Sharafiz Abdul Rahim,Luxin Fan +4 more
4
References
ImageNet classification with deep convolutional neural networks
TL;DR: A large, deep convolutional neural network was trained to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes and employed a recently developed regularization method called "dropout" that proved to be very effective.
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TL;DR: This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features.
You Only Look Once: Unified, Real-Time Object Detection
Joseph Redmon,Santosh K. Divvala,Ross Girshick,Ali Farhadi +3 more
- 27 Jun 2016
TL;DR: Compared to state-of-the-art detection systems, YOLO makes more localization errors but is less likely to predict false positives on background, and outperforms other detection methods, including DPM and R-CNN, when generalizing from natural images to other domains like artwork.
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
Ross Girshick,Jeff Donahue,Trevor Darrell,Jitendra Malik +3 more
- 23 Jun 2014
TL;DR: RCNN as discussed by the authors combines CNNs with bottom-up region proposals to localize and segment objects, and when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost.
Feature Pyramid Networks for Object Detection
Tsung-Yi Lin,Piotr Dollár,Ross Girshick,Kaiming He,Bharath Hariharan,Serge Belongie +5 more
- 21 Jul 2017
TL;DR: This paper exploits the inherent multi-scale, pyramidal hierarchy of deep convolutional networks to construct feature pyramids with marginal extra cost and achieves state-of-the-art single-model results on the COCO detection benchmark without bells and whistles.