My favorite papers from CVPR 2022.

NOTE: this was originally posted on Medium.

Hello! Last June I attended (in person, yeah!) the CVPR 2022 held in New Orleans, with a bunch of cool people from work. I saw some amazing work, talked to a bunch of great people and I’m still processing how to apply what I saw in the challenges that we see.

In the past few weeks I read a bunch of papers and will try to summarize bellow the most interesting things I saw. The majority of the works here are related to face biometrics, since is what we do most here. :-D

Face Recognition

Face recognition still is a hot topic, even thought it’s becoming increasingly hard to beat the SOTA by a significant amount in the current benchmarks.

I’m always interested in works that scale face recognition to millions of identities. One major problem when training in the scale of millions is that the final fully-connected layer scales linearly with the number of identities, resulting in a huge memory footprint and a slow back-propagation time at each iteration. One method that aims to mitigate this, Partial FC [2], was quite popular even before their publication in CVPR this year — it’s included in the popular insightface repo. The method tries to approximate the final layer of now standard training face recognition methods (think CosFace, ArcFace, etc.). With the same purpose of better scaling face recognition, Wang et al. (from Alibaba) method [3] improves even further (see below picture) using a substitute for the FC layer named Dynamic Class Pool and a well-designed data loader.

References

[1] — Kim, M., Jain, A. K., & Liu, X. (2022). AdaFace: Quality Adaptive Margin for Face Recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 18750–18759).

[2] — An, X., Deng, J., Guo, J., Feng, Z., Zhu, X., Yang, J., & Liu, T. (2022). Killing Two Birds with One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4042–4051).

[3] — Wang, K., Wang, S., Zhang, P., Zhou, Z., Zhu, Z., Wang, X., … & You, Y. (2022). An efficient training approach for very large scale face recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4083–4092).

[4] — He, M., Zhang, J., Shan, S., & Chen, X. (2022). Enhancing Face Recognition With Self-Supervised 3D Reconstruction. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4062–4071).

[5] — Phan, H., & Nguyen, A. (2022). DeepFace-EMD: Re-Ranking Using Patch-Wise Earth Mover’s Distance Improves Out-of-Distribution Face Identification. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20259–20269).

[6] — Dhar, P., Kumar, A., Kaplan, K., Gupta, K., Ranjan, R., & Chellappa, R. (2022). EyePAD++: A Distillation-based approach for joint Eye Authentication and Presentation Attack Detection using Periocular Images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20218–20227).

[7] — Wang, C. Y., Lu, Y. D., Yang, S. T., & Lai, S. H. (2022). PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20281–20290).

[8] — Wang, Z., Wang, Z., Yu, Z., Deng, W., Li, J., Gao, T., & Wang, Z. (2022). Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4123–4133).

[9] — Liu, C., Yu, X., Tsai, Y. H., Faraki, M., Moslemi, R., Chandraker, M., & Fu, Y. (2022). Learning to Learn across Diverse Data Biases in Deep Face Recognition. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4072–4082).

[10] — Jung, S., Chun, S., & Moon, T. (2022). Learning Fair Classifiers with Partially Annotated Group Labels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10348–10357).

[11] — Wang, Z., Dong, X., Xue, H., Zhang, Z., Chiu, W., Wei, T., & Ren, K. (2022). Fairness-aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 10379–10388).

[12] — Shiohara, K., & Yamasaki, T. (2022). Detecting Deepfakes with Self-Blended Images. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 18720–18729).

[13] — Jia, S., Ma, C., Yao, T., Yin, B., Ding, S., & Yang, X. (2022). Exploring Frequency Adversarial Attacks for Face Forgery Detection. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4103–4112).

[14] — Zhu, F., Zhu, J., Chu, W., Zhang, X., Ji, X., Wang, C., & Tai, Y. (2022). Blind Face Restoration via Integrating Face Shape and Generative Priors. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 7662–7671).

[15] — Zhao, Yang, Yu-Chuan Su, Chun-Te Chu, Yandong Li, Marius Renn, Yukun Zhu, Changyou Chen, and Xuhui Jia. “Rethinking Deep Face Restoration.” In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp. 7652–7661. 2022.Neural Radiance Fields (NeRFs)

[16] — Verbin, D., Hedman, P., Mildenhall, B., Zickler, T., Barron, J. T., & Srinivasan, P. P. (2021). Ref-nerf: Structured view-dependent appearance for neural radiance fields. arXiv preprint arXiv:2112.03907.

[17] — Athar, S., Xu, Z., Sunkavalli, K., Shechtman, E., & Shu, Z. (2022). RigNeRF: Fully Controllable Neural 3D Portraits. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 20364–20373).

[18] — Rebain, D., Matthews, M., Yi, K. M., Lagun, D., & Tagliasacchi, A. (2022). LOLNeRF: Learn from One Look. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 1558–1567).