0% Complete
Home
/
12th International Conference on Computer and Knowledge Engineering
Pyramid Transformer for Traffic Sign Detection
Authors :
Omid Nejati manzari
1
Amin Boudesh
2
Shahriar B. Shokouhi
3
1- School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
2- Department of Mechanical Engineering, Tarbiat Modares Univesity
3- School of Electrical Engineering, Iran University of Science and Technology, Tehran, Iran
Keywords :
Object Detection،Vision Transformer،Traffic Sign Detection،Self-Driving Cars
Abstract :
Traffic sign detection is a vital task in the visual system of self-driving cars and the automated driving system. Recently, novel Transformerbased models have achieved encouraging results for various computer vision tasks. We still observed that vanilla ViT could not yield satisfactory results in traffic sign detection because the overall size of the datasets is very small and the class distribution of traffic signs is extremely unbalanced. To overcome this problem, a novel Pyramid Transformer with locality mechanisms is proposed in this paper. Specifically, Pyramid Transformer has several spatial pyramid reduction layers to shrink and embed the input image into tokens with rich multi-scale context by using atrous convolutions. Moreover, it inherits an intrinsic scale invariance inductive bias and is able to learn local feature representation for objects at various scales, thereby enhancing the network robustness against the size discrepancy of traffic signs. The experiments are conducted on the German Traffic Sign Detection Benchmark (GTSDB). The results demonstrate the superiority of the proposed model in the traffic sign detection tasks. More specifically, Pyramid Transformer achieves 77.8% mAP on GTSDB when applied to the Cascade RCNN as the backbone, which surpasses most well-known and widely-used state-of-the-art models.
Papers List
List of archived papers
Non-Functional Requirement Extracting Methods for AI-based Systems: A Survey
Reza Damirchi - Amineh Amini
Deep Learning-Driven Beamforming Optimization for High-Performance 5G Planar Antenna Arrays
Rahman Mohammadi - Seyed Reza Razavi Pour
FaaScaler: An Automatic Vertical and Horizontal Scaler for Serverless Computing Environments
Zahra Rezaei - Saeid Abrishami - Seid Nima Moeintaghavi
Underwater Image Super-Resolution using Generative Adversarial Network-based Model
Alireza Aghelan - Modjtaba Rouhani
A New Hypercube Variant: Pruned Shuffle Connected Cube
Reza Latifi - Mahmoud Naghibzadeh
Parallel Local Feature Selection For High-dimensional Data
Zhaleh Manbari - Chiman Salavati - Fardin AkhlaghianTab - Barzan Saeedpoor - Himan Delbina - Mahmud Abdulla Mohammad
Farsi Optical Character Recognition Using a Transformer-based Model
Fatemeh Asadi Zeydabadi - Elham Shabaninia - Hossein Nezamabadi-pour - Melika Shojaee
Histopathology Image-Based Cancer Classification Utilizing Transfer Learning Approach
Amir Meydani - Alireza Meidani - Ali Ramezani - Maryam Shabani - Mohammad Mehdi Kazeminasab - Shahriar Shahablavasani
An influence maximization algorithm based on community detection using topological features
Zahra Aghaee - Afsaneh Fatemi
Improvement of Credit Scoring by LSTM Autoencoder Model
Milad Sattari Maleki - Seyedeh Niusha Motevallian - Faezehsadat Hosseini - Mohammad Sabokrou - Hamidreza Soltanalizadeh Maleki
more
Samin Hamayesh - Version 41.5.3