Litcius/Paper detail

Effects of Shortcut-Level Amount in Lightweight ResNet of ResNet on Object Recognition with Distinct Number of Categories

Aekkasit Krueangsai, Siriporn Supratid

20222022 International Electrical Engineering Congress (iEECON)21 citationsDOI

Abstract

This paper investigates effects of shortcut-level amount in ResNet of ResNet (RoR) based upon lightweight or small-size ResNet11 on object recognition using CIFAR-100 image dataset with different sizes of 10, 50, 100 object categories. Recognition performance comparison among the traditional ResNet11, 1–and 2–shortcut-level ResNet of ResNet (1L- and 2L-RoRs) is evaluated, relying on precision, recall, F1 and accuracy scores, averaged over 10-fold cross validation. Such cross validation is performed to ensure unbiased experimental results. Confusion matrix is also considered for more detail of results investigation. The comparison results indicate ResNet11, 1L- and 2L-RoRs provide best recognition accuracy of 96.38%, 98.70% and 98.55% respectively for 10-, 50- and 100–class CIFAR-100 datasets. It is also noticed the high competency of 2L-RoR on maintaining the recognition performance as increasing the number of data classes, relative to those 1L-RoR and ResNet11. In addition, 2L-RoR model employs only 0.780% more parameters than 1L-RoR; whilst 1L-RoR utilizes a few bits 0.392% higher parameters than ResNet11.

Topics & Concepts

Computer scienceObject (grammar)ConfusionPattern recognition (psychology)Confusion matrixResidual neural networkCognitive neuroscience of visual object recognitionArtificial intelligenceDeep learningPsychologyPsychoanalysisAdvanced Neural Network ApplicationsDomain Adaptation and Few-Shot LearningAdvanced Image and Video Retrieval Techniques
Effects of Shortcut-Level Amount in Lightweight ResNet of ResNet on Object Recognition with Distinct Number of Categories | Litcius