Test results of different models on TinyPerson. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Visual comparison of TinyPerson. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Melanoma Skin Cancer Detection Using Deep Learning Methods and Binary GWO Algorithm by Hussein Ali Bardan (21976208)

“…In this work, we propose a novel framework that integrates </p><p dir="ltr">Convolutional Neural Networks (CNNs) for image classification and a binary Grey Wolf Optimization (GWO) </p><p dir="ltr">algorithm for feature selection. …”

Detection effect comparison on VisDrone2019. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Test results of different models on VisDrone2019. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

datasheet1_Graph Neural Networks for Maximum Constraint Satisfaction.pdf by Jan Tönshoff (10192709)

Structure of YOLOv11 network. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Structure of SEAM network [16]. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Ablation experiment curve. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Experimental environment configuration. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Architecture of BiFPN network [14]. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Datasets label distribution map. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Structure of UAS-YOLO network. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Structure of C3K2_UIB network. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Experimental hyperparameters. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Architecture of ABiFPN network. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Ablation test results. by Ju Liang (4277062)

“…By leveraging dynamic channel attention and spatial feature recalibration, C3K2_UIB suppresses background noise; although this increases parameters by 34%, it achieves improved detection accuracy through efficient feature selection, striking a balance between accuracy and complexity.Experimental results show that on the VisDrone2019 dataset and the TinyPerson dataset from Kaggle, the mean Average Precision (mAP) of the algorithm is increased by 4.9 and 2.1 percentage points, respectively. …”

Table_1_An efficient decision support system for leukemia identification utilizing nature-inspired deep feature optimization.pdf by Muhammad Awais (263096)

“…To optimize feature selection, a customized binary Grey Wolf Algorithm is utilized, achieving an impressive 80% reduction in feature size while preserving key discriminative information. …”