Papers › GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations
GhostFaceNets: Lightweight Face Recognition Model From Cheap Operations
Mohamad Alansari, Oussama Abdul Hay, Sajid Javed, Abdulhadi Shoufan, Yahya Zweiri, Naoufel Werghi
The development of deep learning-based biometric models that can be deployed on devices with constrained memory and computational resources has proven to be a significant challenge. Previous approaches to this problem have not prioritized the reduction of feature map redundancy, but the introduction of Ghost modules represents a major innovation in this area. Ghost modules use a series of inexpensive linear transformations to extract additional feature maps from a set of intrinsic features, allowing for a more comprehensive representation of the underlying information. GhostNetV1 and GhostNetV2, both of which are based on Ghost modules, serve as the foundation for a group of lightweight face recognition models called GhostFaceNets. GhostNetV2 expands upon the original GhostNetV1 by adding an attention mechanism to capture long-range dependencies. Evaluation of GhostFaceNets using various benchmarks reveals that these models offer superior performance while requiring a computational complexity of approximately 60–275 MFLOPs. This is significantly lower than that of State-Of-The-Art (SOTA) big convolutional neural network (CNN) models, which can require hundreds of millions of FLOPs. GhostFaceNets trained with the ArcFace loss on the refined MS-Celeb-1M dataset demonstrate SOTA performance on all benchmarks. In comparison to previous SOTA mobile CNNs, GhostFaceNets greatly improve efficiency for face verification tasks. The GhostFaceNets code is available at: https://github.com/HamadYA/GhostFaceNets .
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Face Identification | MegaFace | GhostFaceNetV2-1 | Accuracy | 98.64% | #5 of 13 | Archive leaderboard | report |
| Face Recognition | CALFW | GhostFaceNetV2-1 | Accuracy | 0.9612 | #3 of 3 | Archive leaderboard | report |
| Face Recognition | CFP-FF | GhostFaceNetV2-1 | Accuracy | 99.9143 | #1 of 1 | Archive leaderboard | report |
| Face Recognition | CFP-FP | GhostFaceNetV2-1 | Accuracy | 0.9933 | #1 of 8 | Archive leaderboard | report |
| Face Recognition | CPLFW | GhostFaceNetV2-1 | Accuracy | 0.9465 | #1 of 2 | Archive leaderboard | report |
| Face Recognition | LFW | GhostFaceNetV2-1 (MS1MV3) | Accuracy | 0.998667 | #1 of 16 | Archive leaderboard | report |
| Face Verification | AgeDB-30 | GhostFaceNetV2-1 | Accuracy | 0.9862 | #2 of 5 | Archive leaderboard | report |
| Face Verification | MegaFace | GhostFaceNetV2-1 | Accuracy | 98.72% | #3 of 12 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections