Partial FC: Training 10 Million Identities on a Single Machine
Xiang An, Xuhan Zhu, Yuan Gao, Xiao Yang, Zhao Yong-le, Ziyong Feng, Lan Wu, Bin Qin, Ming Zhang, Debing Zhang, Ying Fu
Paper appears method- or tooling-adjacent to AI workflows with partial ecosystem coverage.
Face recognition has been an active and vital topic among computer vision community for a long time. Previous researches mainly focus on loss functions used for facial feature extraction network, among which the improvements of softmax-based loss functions greatly promote the performance of face recognition. However, the contradiction between the drastically increasing number of face identities and the shortage of GP ...
U memory is gradually becoming irreconcilable. In this work, we theoretically analyze the upper limit of model parallelism in face recognition in the first place. Then we propose a load-balanced sparse distributed classification training method, Partial FC, which is capable of using a machine with only 8 Nvidia Tesla V100 GPUs to implement training on a face recognition data set with up to 29 million IDs. Furthermore, we are able to train on data set with 100 million IDs in 64 RTX2080Ti GPUs. We have verified the effectiveness of Partial FC in 8 mainstream face recognition trainsets, and find that Partial FC is effective in all face recognition training sets. The code of this paper has been made available at https://github.com/deepinsight/insightface/tree/master/recognition/partial_fc.
Results & Benchmarks
No concrete benchmark grounding is available yet. Treat the page as context or an implementation starting point only.
Face recognition has been an active and vital topic among computer vision community for a long time.
Implementation Evidence Summary
ChanChiChoi/awesome-Face_Recognition is the closest maintained adjacent implementation (Matches contextual method/domain keyword: face detection). It is not paper-verified; validate algorithm and evaluation setup against the paper before trusting reported metrics. Community adoption signal: 4742 GitHub stars.
Reproduction Risks
- Adjacent implementations are not paper-verified
- Recommended repository is adjacent and not paper-verified.
Hardware Notes
Then we propose a load-balanced sparse distributed classification training method, Partial FC, which is capable of using a machine with only 8 Nvidia Tesla V100 GPUs to implement t
Evidence disclosure
Evidence graph: 3 refs, 3 links.
Utility signals: depth 70/100, grounding 75/100, status medium.
Implementation Status
There is no verified maintained implementation yet. Use this baseline plan to decide whether to prototype now or defer.
- No maintained paper-verified implementation was found; start with the closest related repositories below.
- Compare repo methods against the paper equations/algorithm before trusting metrics.
- Create a minimal baseline implementation from the paper and use adjacent repos as references.
Reproduction readiness
Hardware requirements
- Then we propose a load-balanced sparse distributed classification training method, Partial FC, which is capable of using a machine with only 8 Nvidia Tesla V100 GPUs to implement t
No verified implementation available
- · No maintained repository has been identified for this paper. Check adjacent implementations or HF artifacts below.
No benchmark numbers could be verified. You will not be able to validate reproduction correctness against published numbers.
Closest related implementations
These are not paper-verified. Use them as reference points when no direct implementation is available.
- ChanChiChoi/awesome-Face_RecognitionAdjacentConfidence: MediumStars: 4,742
Matches contextual method/domain keyword: face detection
Hugging Face artifacts
No trustworthy direct or curated related Hugging Face artifacts were found yet.
Continue with targeted Hugging Face searches derived from the paper title and method context:
Tip: start with models, then check datasets/spaces if you need evaluation data or demos.
Direct artifact matches are currently sparse. Use targeted Hugging Face searches to quickly locate candidate models, datasets, and demos.
Research context
189
Citations
25
References
Tasks
Computer science, Softmax function, Facial recognition system, Face (sociological concept), Set (abstract data type), Face detection, Code (set theory), Partial evaluation
Methods
None detected
Domains
Artificial intelligence, Machine learning, Computer Vision and Pattern Recognition
Evaluation & Human Feedback Data
Open this paper in HFEPX to review benchmark signals, evaluation modes, and human-feedback protocol context.
Open in HFEPXExplore Similar Papers
Jump to Paper2Code search queries derived from this paper's research context.
Related papers
-
Search on Paper2Code
Sample reconstruction with deep autoencoder for one sample per person face recognition (2017) Semantic similarity
-
Search on Paper2Code
Deep CNN ensemble for recognition of face images (2021) Semantic similarity
-
Search on Paper2Code
A Hybrid Approach to Face Recognition Using Generalized Two-Dimensional Fisher's Linear Discriminant Method (2010) Semantic similarity
-
Search on Paper2Code
Feature extraction by fusing local and global discriminant features: An application to face recognition (2010) Semantic similarity
-
Search on Paper2Code
Fusing Gabor and LBP feature sets for KNN and SRC-based face recognition (2016) Semantic similarity
-
Search on Paper2Code
Face recognition based on synthesis of face images with pose variations (2008) Semantic similarity
Need human evaluators for your AI research? Scale annotation with expert AI Trainers.