Optimization Algorithm to Reduce Training Time for Deep Learning Computer Vision Algorithms Using Large Image Datasets With Tiny Objects

Abstract

The optimization of convolutional neural networks (CNN) generally refers to the improvement of the inference process, making this as fast and precise as possible. While inference time is an essential factor in using these networks in real time, the training of CNNs using very large datasets can be very costly in terms of time and computing power. This paper proposes a technique to reduce training time by an average of 75% without altering the results of CNN training with an algorithm which partitions the dataset and discards superfluous objects (targets). This algorithm is a tool that pre-processes the original dataset, generating a smaller and more condensed dataset to be used for network training. The effectiveness of this tool depends on the type of dataset used for training the CNN and is particularly effective with sequential images (video), large images and images with tiny targets generally from drones or traffic surveillance cameras (but applicable to any other type of image which meets the requirements). The tool can be parameterized to meet the characteristics of the initial dataset.

Clamp Dot Image Classification Using Neural Network

“…To evaluate the performance of the four models, we used a confusion matrix (16) with four quadrants: true positive (TP), (17) false positive (FP), (17) true negative (TN), (17) and false negative (FN), (17) as shown in Fig. 8.…”

An Urban Traffic Dataset Composed of Visible Images and Their Semantic Segmentation Generated by the CARLA Simulator

“…In this work o architectures were not tested. But this does not mean that they have not been teste other networks like TensorFlow (Keras), ResNet, DETR, EfficientDetLite, etc., with sim datasets, as can be seen in [26]. The characteristics of these images (large images, s objects to recognize, objects grouped in an area of the image, low-density areas of ta against other very saturated areas, etc.)…”

Implementation of an Edge-Computing Vision System on Reduced-Board Computers Embedded in UAVs for Intelligent Traffic Management

“…For this purpose, two different input options were used: (1) the original dataset and (2) the same dataset optimized before training. For the second case, the training optimizer developed in the paper titled "Optimization Algorithm to Reduce Training Time for Deep Learning Computer Vision Algorithms Using Large Image Datasets with Tiny Objects" [45] was used. The use of this procedure was due to the dataset in this study fitting perfectly with the constraints and conditions of this algorithm.…”

“…The use of this procedure was due to the dataset in this study fitting perfectly with the constraints and conditions of this algorithm. These constraints, in summary, are as follows [45]:…”