Fetching the paper…

Reading the bibliography…

2023

Face Recognition in the age of CLIP & Billion image datasets

Bhat, Aaditya, Jain, Shrey

Original
PDF
Post on X

Understand

CLIP (Contrastive Language-Image Pre-training) models developed by OpenAI have achieved outstanding results on various image recognition and retrieval tasks, displaying strong zero-shot performance.

This means that they are able to perform effectively on tasks for which they have not been explicitly trained.
Inspired by the success of OpenAI CLIP, a new publicly available dataset called LAION-5B was collected which resulted in the development of open ViT-H/14, ViT-G/14 models that outperform the OpenAI L/14 model.
The LAION-5B dataset also released an approximate nearest neighbor index, with a web interface for search & subset creation.

Face Recognition in the age of CLIP & Billion image datasets · Around

Built on

Liu, Ziwei et al. “Deep Learning Face Attributes in the Wild.” 2015 IEEE International Conference on Computer Vision (ICCV) (2014): 3730-3738
2014
Earlier work this paper cites.
Shan, S., Wenger, E., Zhang, J., Li, H., Zheng, H. & Zhao, B. Fawkes: Protecting Privacy against Unauthorized Deep Learning Models. Proceedings Of The 29th USENIX Conference On Security Symposium
2020
Earlier work this paper cites.

Similar

Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M. & Sutskever, I. Zero-Shot Text-to-Image Generation. Proceedings Of The 38th International Conference On Machine Learning
2021
Cited alongside, same era.
Radford, A., Kim, J., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G. & Sutskever, I. Learning Transferable Visual Models From Natural Language Supervision. Proceedings Of The 38th International Conference On Machine Learning
2021
Cited alongside, same era.
Evani Radiya-Dixit, Sanghyun Hong, Nicholas Carlini, Florian Tramèr. Data Poisoning Won’t Save You From Facial Recognition arXiv:2106.14851
Original
Cited in the paper.
Fawkes- Privacy preserving tool against facial recognition systems. URL: https://github.com/Shawn-Shan/fawkes
Cited in the paper.
BIPA- Biometric Information Privacy Act. URL: https://www.aclu-il.org/en/campaigns/biometric-information-privacy-act-bipa
Cited in the paper.
CLIP: Connecting text and images. URL: https://openai.com/blog/clip/
Cited in the paper.
Easily compute clip embeddings and build a clip retrieval system. URL: https://github.com/rom1504/clip-retrieval
Cited in the paper.
Business and Commerce Code. URL: https://statutes.capitol.texas.gov/Docs/BC/htm/BC.503.htm
Cited in the paper.
Chapter 19.375 RCW- Biometric Identifiers https://app.leg.wa.gov/RCW/default.aspx?cite=19.375&full=true
Cited in the paper.
CLIP Front. https://rom1504.github.io/clip-retrieval/back=https%3A%2F%2Fknn5.laion.ai&index=laion5B&useMclip=false
Cited in the paper.

Then

Cherepanova, V., Goldblum, M., Foley, H., Duan, S., Dickerson, J., Taylor, G. & Goldstein, T. LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition. (arXiv,2021), https://arxiv.org/abs/2101.07922
Original
2021
Later among the works it cites.
Schuhmann, C., Beaumont, R., Vencu, R., Gordon, C., Wightman, R., Cherti, M., Coombes, T., Katta, A., Mullis, C., Wortsman, M., Schramowski, P., Kundurthy, S., Crowson, K., Schmidt, L., Kaczmarczyk, R. & Jitsev, J. LAION-5B: An open large-scale dataset for training next generation image-text models. (arXiv,2022), https://arxiv.org/abs/2210.08402
Original
2022
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…