# Scale Invariant Domain Generalization Image Recapture Detection

arXiv: https://arxiv.org/abs/2110.03496 · HTML: https://mlsanity.com/paper/2110.03496/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 28 references that are in the map.
- First posted on arXiv 7 Oct 2021.

## Builds on (most cited first, 4 of 4)

- [Unsupervised Domain Adaptation by Backpropagation](https://mlsanity.com/paper/1409.7495/) (2014)
- [Domain Generalization via Model-Agnostic Learning of Semantic Features](https://mlsanity.com/paper/1910.13580/) (2019)
- [Single-Side Domain Generalization for Face Anti-Spoofing](https://mlsanity.com/paper/2004.14043/) (2020)
- [Learning scale-variant and scale-invariant features for deep image classification](https://mlsanity.com/paper/1602.01255/) (2016)

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

- [Domain Generalized Recaptured Screen Image Identification Using SWIN Transformer](https://mlsanity.com/paper/2407.17170/) (2024)

## Abstract (arXiv)

Recapturing and rebroadcasting of images are common attack methods in insurance frauds and face identification spoofing, and an increasing number of detection techniques were introduced to handle this problem. However, most of them ignored the domain generalization scenario and scale variances, with an inferior performance on domain shift situations, and normally were exacerbated by intra-domain and inter-domain scale variances. In this paper, we propose a scale alignment domain generalization framework (SADG) to address these challenges. First, an adversarial domain discriminator is exploited to minimize the discrepancies of image representation distributions among different domains. Meanwhile, we exploit triplet loss as a local constraint to achieve a clearer decision boundary. Moreover, a scale alignment loss is introduced as a global relationship regularization to force the image representations of the same class across different scales to be undistinguishable. Experimental results on four databases and comparison with state-of-the-art approaches show that better performance can be achieved using our framework.