AsArcFace: Asymmetric Additive Angular Margin Loss for Fairface Recognition

Zhou, Shengyao; Luo, Jie; Zhou, Junkun; Xiang, Ji

doi:10.1007/978-3-030-65414-6_33

Cited by 2 publications

(2 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…al. [72] used hand-crafted patch-level features to encode an image for ranking and then used multiple reference images in the database to re-rank each top-k candidate. The social context between two identities has also been found to be useful in re-ranking photo-tagging results [13].…”

Section: Related Workmentioning

confidence: 99%

“…[54] found that harnessing an external "disambiguator" network trained to separate a query from lookalikes is an effective re-ranking method. In contrast to the prior work, we do not use extra images [72] or external knowledge [13]. Instead, we only re-use state-of-the-art deep models and reranks candidates based on a pair-wise similarity score computed from both the image-level and patch-level similarity.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification

Phan¹,

Nguyen²

2021

Preprint

View full text Add to dashboard Cite

Face identification (FI) is ubiquitous and drives many high-stake decisions made by the law enforcement. Stateof-the-art FI approaches compare two images by taking the cosine similarity between their image embeddings. Yet, such approach suffers from poor out-of-distribution (OOD) generalization to new types of images (e.g., when a query face is masked, cropped or rotated) not included in the training set or the gallery. Here, we propose a re-ranking approach that compares two faces using the Earth Mover's Distance on the deep, spatial features of image patches. Our extra comparison stage explicitly examines image similarity at a fine-grained level (e.g., eyes to eyes) and is more robust to OOD perturbations and occlusions than traditional FI. Interestingly, without finetuning feature extractors, our method consistently improves the accuracy on all tested OOD queries: masked, cropped, rotated, and adversarial while obtaining similar results on in-distribution images.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification

Phan¹,

Nguyen²

2021

Preprint

View full text Add to dashboard Cite

show abstract

FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition

Sixta

Júnior

Buch-Cardona

et al. 2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This work summarizes the 2020 ChaLearn Looking at People Fair Face Recognition and Analysis Challenge and provides a description of the top-winning solutions and analysis of the results. The aim of the challenge was to evaluate accuracy and bias in gender and skin colour of submitted algorithms on the task of 1:1 face verification in the presence of other confounding attributes. Participants were evaluated using an in-the-wild dataset based on reannotated IJB-C, further enriched by 12.5K new images and additional labels. The dataset is not balanced, which simulates a real world scenario where AI-based models supposed to present fair outcomes are trained and evaluated on imbalanced data. The challenge attracted 151 participants, who made more than 1.8K submissions in total. The final phase of the challenge attracted 36 active teams out of which 10 exceeded 0.999 AUC-ROC while achieving very low scores in the proposed bias metrics. Common strategies by the participants were face pre-processing, homogenization of data distributions, the use of bias aware loss functions and ensemble models. The analysis of top-10 teams shows higher false positive rates (and lower false negative rates) for females with dark skin tone as well as the potential of eyeglasses and young age to increase the false positive rates too.

show abstract

AsArcFace: Asymmetric Additive Angular Margin Loss for Fairface Recognition

Cited by 2 publications

References 11 publications

DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification

DeepFace-EMD: Re-ranking Using Patch-wise Earth Mover's Distance Improves Out-Of-Distribution Face Identification

FairFace Challenge at ECCV 2020: Analyzing Bias in Face Recognition

Contact Info

Product

Resources

About