ReSTiNet : On improving the performance of Tiny-YOLO-Based CNN architecture for applications in human detection

• Main Authors: Sumit, Shahriar Shakir, Awang Rambli, Dayang Rohaya, Mirjalili, Seyedali, Ejaz, Muhammad Mudassir, Miah, Md Saef Ullah
• Format: Article
• Language: English
• Published: MDPI 2022
• Subjects: QA75 Electronic computers. Computer science; QA76 Computer software; T Technology (General); TA Engineering (General). Civil engineering (General)
• Online Access: http://umpir.ump.edu.my/id/eprint/37442/1/ReSTiNet_On%20improving%20the%20performance%20of%20tiny-yolo-based%20cnn%20architecture%20for%20applications%20in%20human%20detection.pdf; http://umpir.ump.edu.my/id/eprint/37442/; https://doi.org/10.3390/app12189331; https://doi.org/10.3390/app12189331

Human detection is a special application of object recognition and is considered one of the greatest challenges in computer vision. It is the starting point of a number of applications, including public safety and security surveillance around the world. Human detection technologies have advanced significantly in recent years due to the rapid development of deep learning techniques. Despite recent advances, we still need to adopt the best network-design practices that enable compact sizes, deep designs, and fast training times while maintaining high accuracies. In this article, we propose ReSTiNet, a novel compressed convolutional neural network that addresses the issues of size, detection speed, and accuracy. Following SqueezeNet, ReSTiNet adopts the fire modules by examining the number of fire modules and their placement within the model to reduce the number of parameters and thus the model size. The residual connections within the fire modules in ReSTiNet are interpolated and finely constructed to improve feature propagation and ensure the largest possible information flow in the model, with the goal of further improving the proposed ReSTiNet in terms of detection speed and accuracy. The proposed algorithm downsizes the previously popular Tiny-YOLO model and improves the following features: (1) faster detection speed; (2) compact model size; (3) solving the overfitting problems; and (4) superior performance than other lightweight models such as MobileNet and SqueezeNet in terms of mAP. The proposed model was trained and tested using MS COCO and Pascal VOC datasets. The resulting ReSTiNet model is 10.7 MB in size (almost five times smaller than Tiny-YOLO), but it achieves an mAP of 63.74% on PASCAL VOC and 27.3% on MS COCO datasets using Tesla k80 GPU.