# Grains of Saliency: Optimizing Saliency-based Training of Biometric Attack Detection Models

arXiv: https://arxiv.org/abs/2405.00650 · HTML: https://mlsanity.com/paper/2405.00650/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 45 references that are in the map.
- First posted on arXiv 1 May 2024.

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Training Generative Adversarial Networks with Limited Data](https://mlsanity.com/paper/2006.06676/) (2020)
- [Alias-Free Generative Adversarial Networks](https://mlsanity.com/paper/2106.12423/) (2021)
- [StarGAN v2: Diverse Image Synthesis for Multiple Domains](https://mlsanity.com/paper/1912.01865/) (2019)
- [BiSeNet: Bilateral Segmentation Network for Real-time Semantic Segmentation](https://mlsanity.com/paper/1808.00897/) (2018)
- [Tune: A Research Platform for Distributed Model Selection and Training](https://mlsanity.com/paper/1807.05118/) (2018)
- [CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning](https://mlsanity.com/paper/2112.00686/) (2021)
- [Post-mortem Iris Recognition with Deep-Learning-based Image Segmentation](https://mlsanity.com/paper/1901.01708/) (2019)
- [Iris Liveness Detection Competition (LivDet-Iris) -- The 2020 Edition](https://mlsanity.com/paper/2009.00749/) (2020)
- [Human-Aided Saliency Maps Improve Generalization of Deep Learning](https://mlsanity.com/paper/2105.03492/) (2021)
- [GazeGNN: A Gaze-Guided Graph Neural Network for Chest X-ray Classification](https://mlsanity.com/paper/2305.18221/) (2023)
- [Assessment of iris recognition reliability for eyes affected by ocular pathologies](https://mlsanity.com/paper/1809.00206/) (2018)
- [LivDet in Action - Fingerprint Liveness Detection Competition 2019](https://mlsanity.com/paper/1905.00639/) (2019)
- [Iris Presentation Attack Detection: Where Are We Now?](https://mlsanity.com/paper/2006.13252/) (2020)
- [Iris Liveness Detection Competition (LivDet-Iris) -- The 2023 Edition](https://mlsanity.com/paper/2310.04541/) (2023)
- [SREFI: Synthesis of Realistic Example Face Images](https://mlsanity.com/paper/1704.06693/) (2017)
- [LivDet 2021 Fingerprint Liveness Detection Competition -- Into the unknown](https://mlsanity.com/paper/2108.10183/) (2021)
- [Probabilistic Integration of Object Level Annotations in Chest X-ray Classification](https://mlsanity.com/paper/2210.06980/) (2022)
- [Explain To Me: Salience-Based Explainability for Synthetic Face Detection Models](https://mlsanity.com/paper/2303.11969/) (2023)
- [Taking Training Seriously: Human Guidance and Management-Based Regulation of Artificial Intelligence](https://mlsanity.com/paper/2402.08466/) (2024)
- [Image Complexity Guided Network Compression for Biomedical Image Segmentation](https://mlsanity.com/paper/2107.02927/) (2021)

## Built on by (most cited first, 4 of 4)

- [Saliency-Guided Training for Fingerprint Presentation Attack Detection](https://mlsanity.com/paper/2505.02176/) (2025)
- [Almost Right: Making First-Layer Kernels Nearly Orthogonal Improves Model Generalization](https://mlsanity.com/paper/2504.16362/) (2025)
- [SAGE: Saliency-Guided Contrastive Embeddings](https://mlsanity.com/paper/2511.12744/) (2025)
- [What's Old is New Again: Classical Dimensionality Reduction for Efficient Saliency-Guided Biometric Attack Detection](https://mlsanity.com/paper/2606.13528/) (2026)

## Abstract (arXiv)

Incorporating human-perceptual intelligence into model training has shown to increase the generalization capability of models in several difficult biometric tasks, such as presentation attack detection (PAD) and detection of synthetic samples. After the initial collection phase, human visual saliency (e.g., eye-tracking data, or handwritten annotations) can be integrated into model training through attention mechanisms, augmented training samples, or through human perception-related components of loss functions. Despite their successes, a vital, but seemingly neglected, aspect of any saliency-based training is the level of salience granularity (e.g., bounding boxes, single saliency maps, or saliency aggregated from multiple subjects) necessary to find a balance between reaping the full benefits of human saliency and the cost of its collection. In this paper, we explore several different levels of salience granularity and demonstrate that increased generalization capabilities of PAD and synthetic face detection can be achieved by using simple yet effective saliency post-processing techniques across several different CNNs.