Table 8 Computational complexity comparison between better-performing Stand-alone models and the ensemble model.

From: Enhancing occluded and standard bird object recognition using fuzzy-based ensembled computer vision approach with convolutional neural network

Approach/

model

A

FS

MAC

MAC

AIT

(%)

(%)

(GMAC)

(Million)

(ms)

Densenet121

95.07

95.13

2.9

7.01

16.259

Densenet169

94.96

94.94

3.44

12.58

23.579

Resnet101

96.04

96.02

7.86

42.61

12.449

Simple

Ensemble

Learning

97.56

97.58

14.2

62.2

11.233

Fuzzy-Based

Ensemble

Learning

98.73

98.75

14.2

62.2

30.941

  1. A - Accuracy, FS – F1-Score, MAC - Multiply-Accumulate Operations, CoP - Computational Parameters, AIT - Average Inference Time per Image.
Back to article page