# A-PixelHop: A Green, Robust and Explainable Fake-Image Detector

arXiv: https://arxiv.org/abs/2111.04012 · HTML: https://mlsanity.com/paper/2111.04012/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 7 Nov 2021.

## Builds on (most cited first, 16 of 16)

- [A Style-Based Generator Architecture for Generative Adversarial Networks](https://mlsanity.com/paper/1812.04948/) (2018)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [FaceForensics++: Learning to Detect Manipulated Facial Images](https://mlsanity.com/paper/1901.08971/) (2019)
- [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)
- [Learning to See in the Dark](https://mlsanity.com/paper/1805.01934/) (2018)
- [Detecting and Simulating Artifacts in GAN Fake Images](https://mlsanity.com/paper/1907.06515/) (2019)
- [Photographic Image Synthesis with Cascaded Refinement Networks](https://mlsanity.com/paper/1707.09405/) (2017)
- [Diverse Image Synthesis from Semantic Layouts via Conditional IMLE](https://mlsanity.com/paper/1811.12373/) (2018)
- [Recasting Residual-based Local Descriptors as Convolutional Neural Networks: an Application to Image Forgery Detection](https://mlsanity.com/paper/1703.04615/) (2017)
- [Interpretable Convolutional Neural Networks via Feedforward Design](https://mlsanity.com/paper/1810.02786/) (2018)
- [PointHop: An Explainable Machine Learning Method for Point Cloud Classification](https://mlsanity.com/paper/1907.12766/) (2019)
- [DefakeHop: A Light-Weight High-Performance Deepfake Detector](https://mlsanity.com/paper/2103.06929/) (2021)

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

- [Green Learning: Introduction, Examples and Outlook](https://mlsanity.com/paper/2210.00965/) (2022)
- [PAGER: Progressive Attribute-Guided Extendable Robust Image Generation](https://mlsanity.com/paper/2206.00162/) (2022)
- [Enhancing Edge Intelligence with Highly Discriminant LNT Features](https://mlsanity.com/paper/2312.14968/) (2023)
- [Acceleration of Subspace Learning Machine via Particle Swarm Optimization and Parallel Processing](https://mlsanity.com/paper/2208.07023/) (2022)
- [Green Steganalyzer: A Green Learning Approach to Image Steganalysis](https://mlsanity.com/paper/2306.04008/) (2023)
- [Towards Sustainable Universal Deepfake Detection with Frequency-Domain Masking](https://mlsanity.com/paper/2512.08042/) (2025)
- [Position: AI/ML Deepfake Research is Misaligned with AI-Generated Non-Consensual Intimate Imagery (AIG-NCII)](https://mlsanity.com/paper/2607.18263/) (2026)

## Abstract (arXiv)

A novel method for detecting CNN-generated images, called Attentive PixelHop (or A-PixelHop), is proposed in this work. It has three advantages: 1) low computational complexity and a small model size, 2) high detection performance against a wide range of generative models, and 3) mathematical transparency. A-PixelHop is designed under the assumption that it is difficult to synthesize high-quality, high-frequency components in local regions. It contains four building modules: 1) selecting edge/texture blocks that contain significant high-frequency components, 2) applying multiple filter banks to them to obtain rich sets of spatial-spectral responses as features, 3) feeding features to multiple binary classifiers to obtain a set of soft decisions, 4) developing an effective ensemble scheme to fuse the soft decisions into the final decision. Experimental results show that A-PixelHop outperforms state-of-the-art methods in detecting CycleGAN-generated images. Furthermore, it can generalize well to unseen generative models and datasets.