# A Principled Design of Image Representation: Towards Forensic Tasks

arXiv: https://arxiv.org/abs/2203.00913 · HTML: https://mlsanity.com/paper/2203.00913/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 77 references that are in the map.
- First posted on arXiv 2 Mar 2022.

## Builds on (most cited first, 18 of 18)

- [Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges](https://mlsanity.com/paper/2104.13478/) (2021)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [A Survey on Neural Network Interpretability](https://mlsanity.com/paper/2012.14261/) (2020)
- [HPatches: A benchmark and evaluation of handcrafted and learned local descriptors](https://mlsanity.com/paper/1704.05939/) (2017)
- [The Creation and Detection of Deepfakes: A Survey](https://mlsanity.com/paper/2004.11138/) (2020)
- [Understanding image representations by measuring their equivariance and equivalence](https://mlsanity.com/paper/1411.5908/) (2014)
- [Media Forensics and DeepFakes: an overview](https://mlsanity.com/paper/2001.06564/) (2020)
- [Noiseprint: a CNN-based camera model fingerprint](https://mlsanity.com/paper/1808.08396/) (2018)
- [Rotation equivariant vector field networks](https://mlsanity.com/paper/1612.09346/) (2016)
- [DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms](https://mlsanity.com/paper/2006.07634/) (2020)
- [A Mathematical Theory of Deep Convolutional Neural Networks for Feature Extraction](https://mlsanity.com/paper/1512.06293/) (2015)
- [Towards Robust Pattern Recognition: A Review](https://mlsanity.com/paper/2006.06976/) (2020)
- [DASC: Robust Dense Descriptor for Multi-modal and Multi-spectral Correspondence Estimation](https://mlsanity.com/paper/1604.07944/) (2016)
- [A Survey of Orthogonal Moments for Image Representation: Theory, Implementation, and Evaluation](https://mlsanity.com/paper/2103.14799/) (2021)
- [A comparison of dense region detectors for image search and fine-grained classification](https://mlsanity.com/paper/1410.8151/) (2014)
- [Dense scale selection over space, time and space-time](https://mlsanity.com/paper/1709.08603/) (2017)

## Built on by (most cited first, 8 of 8)

- [Pixel-Inconsistency Modeling for Image Manipulation Localization](https://mlsanity.com/paper/2310.00234/) (2023)
- [Code-in-the-Loop Forensics: Agentic Tool Use for Image Forgery Detection](https://mlsanity.com/paper/2512.16300/) (2025)
- [Webly-Supervised Image Manipulation Localization via Category-Aware Auto-Annotation](https://mlsanity.com/paper/2508.20987/) (2025)
- [Representing Noisy Image Without Denoising](https://mlsanity.com/paper/2301.07409/) (2023)
- [Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum](https://mlsanity.com/paper/2503.08484/) (2025)
- [Spatial-Frequency Discriminability for Revealing Adversarial Perturbations](https://mlsanity.com/paper/2305.10856/) (2023)
- [Hierarchical Invariance for Robust and Interpretable Vision Tasks at Larger Scales](https://mlsanity.com/paper/2402.15430/) (2024)
- [Image Copy-Move Forgery Detection and Localization Scheme: How to Avoid Missed Detection and False Alarm](https://mlsanity.com/paper/2406.03271/) (2024)

## Abstract (arXiv)

Image forensics is a rising topic as the trustworthy multimedia content is critical for modern society. Like other vision-related applications, forensic analysis relies heavily on the proper image representation. Despite the importance, current theoretical understanding for such representation remains limited, with varying degrees of neglect for its key role. For this gap, we attempt to investigate the forensic-oriented image representation as a distinct problem, from the perspectives of theory, implementation, and application. Our work starts from the abstraction of basic principles that the representation for forensics should satisfy, especially revealing the criticality of robustness, interpretability, and coverage. At the theoretical level, we propose a new representation framework for forensics, called Dense Invariant Representation (DIR), which is characterized by stable description with mathematical guarantees. At the implementation level, the discrete calculation problems of DIR are discussed, and the corresponding accurate and fast solutions are designed with generic nature and constant complexity. We demonstrate the above arguments on the dense-domain pattern detection and matching experiments, providing comparison results with state-of-the-art descriptors. Also, at the application level, the proposed DIR is initially explored in passive and active forensics, namely copy-move forgery detection and perceptual hashing, exhibiting the benefits in fulfilling the requirements of such forensic tasks.