# Trading-off Mutual Information on Feature Aggregation for Face Recognition

arXiv: https://arxiv.org/abs/2309.13137 · HTML: https://mlsanity.com/paper/2309.13137/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 51 references that are in the map.
- First posted on arXiv 22 Sep 2023.

## Builds on (most cited first, 29 of 29)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks](https://mlsanity.com/paper/1905.11946/) (2019)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Averaging Weights Leads to Wider Optima and Better Generalization](https://mlsanity.com/paper/1803.05407/) (2018)
- [CosFace: Large Margin Cosine Loss for Deep Face Recognition](https://mlsanity.com/paper/1801.09414/) (2018)
- [Deep Variational Information Bottleneck](https://mlsanity.com/paper/1612.00410/) (2016)
- [CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification](https://mlsanity.com/paper/2103.14899/) (2021)
- [SphereFace: Deep Hypersphere Embedding for Face Recognition](https://mlsanity.com/paper/1704.08063/) (2017)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (2018)
- [Deep metric learning using Triplet network](https://mlsanity.com/paper/1412.6622/) (2014)
- [AdaFace: Quality Adaptive Margin for Face Recognition](https://mlsanity.com/paper/2204.00964/) (2022)
- [Rethinking Spatial Dimensions of Vision Transformers](https://mlsanity.com/paper/2103.16302/) (2021)
- [MagFace: A Universal Representation for Face Recognition and Quality Assessment](https://mlsanity.com/paper/2103.06627/) (2021)
- [CurricularFace: Adaptive Curriculum Learning Loss for Deep Face Recognition](https://mlsanity.com/paper/2004.00288/) (2020)
- [Large-Margin Softmax Loss for Convolutional Neural Networks](https://mlsanity.com/paper/1612.02295/) (2016)
- [Ensemble deep learning: A review](https://mlsanity.com/paper/2104.02395/) (2021)
- [Video Transformer Network](https://mlsanity.com/paper/2102.00719/) (2021)
- [Cross-Age LFW: A Database for Studying Cross-Age Face Recognition in Unconstrained Environments](https://mlsanity.com/paper/1708.08197/) (2017)
- [Incorporating Convolution Designs into Visual Transformers](https://mlsanity.com/paper/2103.11816/) (2021)
- [WebFace260M: A Benchmark Unveiling the Power of Million-Scale Deep Face Recognition](https://mlsanity.com/paper/2103.04098/) (2021)
- [Transformer-based Multimodal Information Fusion for Facial Expression Analysis](https://mlsanity.com/paper/2203.12367/) (2022)
- [BroadFace: Looking at Tens of Thousands of People at Once for Face Recognition](https://mlsanity.com/paper/2008.06674/) (2020)
- [Frequency Disentangled Features in Neural Image Compression](https://mlsanity.com/paper/2308.02620/) (2023)
- [More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learning](https://mlsanity.com/paper/2307.00651/) (2023)
- [AAFACE: Attribute-aware Attentional Network for Face Recognition](https://mlsanity.com/paper/2308.07243/) (2023)

## Built on by (most cited first, 1 of 1)

- [A Novel Approach to Chest X-ray Lung Segmentation Using U-net and Modified Convolutional Block Attention Module](https://mlsanity.com/paper/2404.14322/) (2024)

## Abstract (arXiv)

Despite the advances in the field of Face Recognition (FR), the precision of these methods is not yet sufficient. To improve the FR performance, this paper proposes a technique to aggregate the outputs of two state-of-the-art (SOTA) deep FR models, namely ArcFace and AdaFace. In our approach, we leverage the transformer attention mechanism to exploit the relationship between different parts of two feature maps. By doing so, we aim to enhance the overall discriminative power of the FR system. One of the challenges in feature aggregation is the effective modeling of both local and global dependencies. Conventional transformers are known for their ability to capture long-range dependencies, but they often struggle with modeling local dependencies accurately. To address this limitation, we augment the self-attention mechanism to capture both local and global dependencies effectively. This allows our model to take advantage of the overlapping receptive fields present in corresponding locations of the feature maps. However, fusing two feature maps from different FR models might introduce redundancies to the face embedding. Since these models often share identical backbone architectures, the resulting feature maps may contain overlapping information, which can mislead the training process. To overcome this problem, we leverage the principle of Information Bottleneck to obtain a maximally informative facial representation. This ensures that the aggregated features retain the most relevant and discriminative information while minimizing redundant or misleading details. To evaluate the effectiveness of our proposed method, we conducted experiments on popular benchmarks and compared our results with state-of-the-art algorithms. The consistent improvement we observed in these benchmarks demonstrates the efficacy of our approach in enhancing FR performance.