# One-to-many face recognition with bilinear CNNs

arXiv: https://arxiv.org/abs/1506.01342 · HTML: https://mlsanity.com/paper/1506.01342/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 3 Jun 2015.

## Built on by (most cited first, 7 of 7)

- [CoNAN: Conditional Neural Aggregation Network For Unconstrained Face Feature Fusion](https://mlsanity.com/paper/2307.10237/) (2023)
- [Open-Set Face Recognition with Maximal Entropy and Objectosphere Loss](https://mlsanity.com/paper/2311.00400/) (2023)
- [Deep face recognition with clustering based domain adaptation](https://mlsanity.com/paper/2205.13937/) (2022)
- [Quality-Aware Multimodal Biometric Recognition](https://mlsanity.com/paper/2112.05827/) (2021)
- [A NIR-to-VIS face recognition via part adaptive and relation attention module](https://mlsanity.com/paper/2102.00689/) (2021)
- [Adaptive Face Recognition Using Adversarial Information Network](https://mlsanity.com/paper/2305.13605/) (2023)
- [Efficient aggregation of face embeddings for decentralized face recognition deployments (extended version)](https://mlsanity.com/paper/2212.10108/) (2022)

## Abstract (arXiv)

The recent explosive growth in convolutional neural network (CNN) research has produced a variety of new architectures for deep learning. One intriguing new architecture is the bilinear CNN (B-CNN), which has shown dramatic performance gains on certain fine-grained recognition problems [15]. We apply this new CNN to the challenging new face recognition benchmark, the IARPA Janus Benchmark A (IJB-A) [12]. It features faces from a large number of identities in challenging real-world conditions. Because the face images were not identified automatically using a computerized face detection system, it does not have the bias inherent in such a database. We demonstrate the performance of the B-CNN model beginning from an AlexNet-style network pre-trained on ImageNet. We then show results for fine-tuning using a moderate-sized and public external database, FaceScrub [17]. We also present results with additional fine-tuning on the limited training data provided by the protocol. In each case, the fine-tuned bilinear model shows substantial improvements over the standard CNN. Finally, we demonstrate how a standard CNN pre-trained on a large face database, the recently released VGG-Face model [20], can be converted into a B-CNN without any additional feature training. This B-CNN improves upon the CNN performance on the IJB-A benchmark, achieving 89.5% rank-1 recall.