GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection
To address the issues of target feature blurring and increased false detections caused by high compression rates in deepfake videos, as well as the high computational resource requirements of existing face extractors, we propose a lightweight face extractor to assist deepfake detection, GCS-YOLOv8....
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/21/6781 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846173154348630016 |
|---|---|
| author | Ruifang Zhang Bohan Deng Xiaohui Cheng Hong Zhao |
| author_facet | Ruifang Zhang Bohan Deng Xiaohui Cheng Hong Zhao |
| author_sort | Ruifang Zhang |
| collection | DOAJ |
| description | To address the issues of target feature blurring and increased false detections caused by high compression rates in deepfake videos, as well as the high computational resource requirements of existing face extractors, we propose a lightweight face extractor to assist deepfake detection, GCS-YOLOv8. Firstly, we employ the HGStem module for initial downsampling to address the issue of false detections of small non-face objects in deepfake videos, thereby improving detection accuracy. Secondly, we introduce the C2f-GDConv module to mitigate the low-FLOPs pitfall while reducing the model’s parameters, thereby lightening the network. Additionally, we add a new P6 large target detection layer to expand the receptive field and capture multi-scale features, solving the problem of detecting large-scale faces in low-compression deepfake videos. We also design a cross-scale feature fusion module called CCFG (CNN-based Cross-Scale Feature Fusion with GDConv), which integrates features from different scales to enhance the model’s adaptability to scale variations while reducing network parameters, addressing the high computational resource requirements of traditional face extractors. Furthermore, we improve the detection head by utilizing group normalization and shared convolution, simplifying the process of face detection while maintaining detection performance. The training dataset was also refined by removing low-accuracy and low-resolution labels, which reduced the false detection rate. Experimental results demonstrate that, compared to YOLOv8, this face extractor achieves the AP of 0.942, 0.927, and 0.812 on the WiderFace dataset’s Easy, Medium, and Hard subsets, representing improvements of 1.1%, 1.3%, and 3.7% respectively. The model’s parameters and FLOPs are only 1.68 MB and 3.5 G, reflecting reductions of 44.2% and 56.8%, making it more effective and lightweight in extracting faces from deepfake videos. |
| format | Article |
| id | doaj-art-30b1f7da5abd456392e6a0b78ca1a5fb |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-30b1f7da5abd456392e6a0b78ca1a5fb2024-11-08T14:40:55ZengMDPI AGSensors1424-82202024-10-012421678110.3390/s24216781GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake DetectionRuifang Zhang0Bohan Deng1Xiaohui Cheng2Hong Zhao3Key Laboratory of Advanced Manufacturing and Automation Technology, Education Department of Guangxi Zhuang Autonomous Region, Guilin University of Technology, Guilin 541006, ChinaKey Laboratory of Advanced Manufacturing and Automation Technology, Education Department of Guangxi Zhuang Autonomous Region, Guilin University of Technology, Guilin 541006, ChinaCollege of Information Science and Engineering, Guilin University of Technology, Guilin 541006, ChinaKey Laboratory of Advanced Manufacturing and Automation Technology, Education Department of Guangxi Zhuang Autonomous Region, Guilin University of Technology, Guilin 541006, ChinaTo address the issues of target feature blurring and increased false detections caused by high compression rates in deepfake videos, as well as the high computational resource requirements of existing face extractors, we propose a lightweight face extractor to assist deepfake detection, GCS-YOLOv8. Firstly, we employ the HGStem module for initial downsampling to address the issue of false detections of small non-face objects in deepfake videos, thereby improving detection accuracy. Secondly, we introduce the C2f-GDConv module to mitigate the low-FLOPs pitfall while reducing the model’s parameters, thereby lightening the network. Additionally, we add a new P6 large target detection layer to expand the receptive field and capture multi-scale features, solving the problem of detecting large-scale faces in low-compression deepfake videos. We also design a cross-scale feature fusion module called CCFG (CNN-based Cross-Scale Feature Fusion with GDConv), which integrates features from different scales to enhance the model’s adaptability to scale variations while reducing network parameters, addressing the high computational resource requirements of traditional face extractors. Furthermore, we improve the detection head by utilizing group normalization and shared convolution, simplifying the process of face detection while maintaining detection performance. The training dataset was also refined by removing low-accuracy and low-resolution labels, which reduced the false detection rate. Experimental results demonstrate that, compared to YOLOv8, this face extractor achieves the AP of 0.942, 0.927, and 0.812 on the WiderFace dataset’s Easy, Medium, and Hard subsets, representing improvements of 1.1%, 1.3%, and 3.7% respectively. The model’s parameters and FLOPs are only 1.68 MB and 3.5 G, reflecting reductions of 44.2% and 56.8%, making it more effective and lightweight in extracting faces from deepfake videos.https://www.mdpi.com/1424-8220/24/21/6781deepfakeface extractionlightweightYOLOv8HGStemC2f-GDConv |
| spellingShingle | Ruifang Zhang Bohan Deng Xiaohui Cheng Hong Zhao GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection Sensors deepfake face extraction lightweight YOLOv8 HGStem C2f-GDConv |
| title | GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection |
| title_full | GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection |
| title_fullStr | GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection |
| title_full_unstemmed | GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection |
| title_short | GCS-YOLOv8: A Lightweight Face Extractor to Assist Deepfake Detection |
| title_sort | gcs yolov8 a lightweight face extractor to assist deepfake detection |
| topic | deepfake face extraction lightweight YOLOv8 HGStem C2f-GDConv |
| url | https://www.mdpi.com/1424-8220/24/21/6781 |
| work_keys_str_mv | AT ruifangzhang gcsyolov8alightweightfaceextractortoassistdeepfakedetection AT bohandeng gcsyolov8alightweightfaceextractortoassistdeepfakedetection AT xiaohuicheng gcsyolov8alightweightfaceextractortoassistdeepfakedetection AT hongzhao gcsyolov8alightweightfaceextractortoassistdeepfakedetection |