# Improving Model's Focus Improves Performance of Deep Learning-Based Synthetic Face Detectors

arXiv: https://arxiv.org/abs/2303.00818 · HTML: https://mlsanity.com/paper/2303.00818/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 1 Mar 2023.

## Builds on (most cited first, 19 of 19)

- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [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)
- [Learning Deep Features for Discriminative Localization](https://mlsanity.com/paper/1512.04150/) (2015)
- [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: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Thinking in Frequency: Face Forgery Detection by Mining Frequency-aware Clues](https://mlsanity.com/paper/2007.09355/) (2020)
- [This Face Does Not Exist ... But It Might Be Yours! Identity Leakage in Generative Models](https://mlsanity.com/paper/2101.05084/) (2020)
- [CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning](https://mlsanity.com/paper/2112.00686/) (2021)
- [Domain-Specific Human-Inspired Binarized Statistical Image Features for Iris Recognition](https://mlsanity.com/paper/1807.05248/) (2018)
- [Visual Psychophysics for Making Face Recognition Algorithms More Explainable](https://mlsanity.com/paper/1803.07140/) (2018)
- [Training CNNs in Presence of JPEG Compression: Multimedia Forensics vs Computer Vision](https://mlsanity.com/paper/2009.12088/) (2020)
- [SREFI: Synthesis of Realistic Example Face Images](https://mlsanity.com/paper/1704.06693/) (2017)
- [Performance of Humans in Iris Recognition: The Impact of Iris Condition and Annotation-driven Verification](https://mlsanity.com/paper/1807.05245/) (2018)
- [Measuring Human Perception to Improve Handwritten Document Transcription](https://mlsanity.com/paper/1904.03734/) (2019)
- [Haven't I Seen You Before? Assessing Identity Leakage in Synthetic Irises](https://mlsanity.com/paper/2211.05629/) (2022)

## Abstract (arXiv)

Deep learning-based models generalize better to unknown data samples after being guided "where to look" by incorporating human perception into training strategies. We made an observation that the entropy of the model's salience trained in that way is lower when compared to salience entropy computed for models training without human perceptual intelligence. Thus the question: does further increase of model's focus, by lowering the entropy of model's class activation map, help in further increasing the performance? In this paper we propose and evaluate several entropy-based new loss function components controlling the model's focus, covering the full range of the level of such control, from none to its "aggressive" minimization. We show, using a problem of synthetic face detection, that improving the model's focus, through lowering entropy, leads to models that perform better in an open-set scenario, in which the test samples are synthesized by unknown generative models. We also show that optimal performance is obtained when the model's loss function blends three aspects: regular classification, low-entropy of the model's focus, and human-guided saliency.