# Combining Contrastive and Supervised Learning for Video Super-Resolution Detection

arXiv: https://arxiv.org/abs/2205.10406 · HTML: https://mlsanity.com/paper/2205.10406/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 33 references that are in the map.
- First posted on arXiv 20 May 2022.

## Builds on (most cited first, 22 of 22)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [SwinIR: Image Restoration Using Swin Transformer](https://mlsanity.com/paper/2108.10257/) (2021)
- [Improved Regularization of Convolutional Neural Networks with Cutout](https://mlsanity.com/paper/1708.04552/) (2017)
- [ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks](https://mlsanity.com/paper/1809.00219/) (2018)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data](https://mlsanity.com/paper/2107.10833/) (2021)
- [CNN-generated images are surprisingly easy to spot... for now](https://mlsanity.com/paper/1912.11035/) (2019)
- [Image Transformer](https://mlsanity.com/paper/1802.05751/) (2018)
- [Video Enhancement with Task-Oriented Flow](https://mlsanity.com/paper/1711.09078/) (2017)
- [Toward Real-World Single Image Super-Resolution: A New Benchmark and A New Model](https://mlsanity.com/paper/1904.00523/) (2019)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [TDAN: Temporally Deformable Alignment Network for Video Super-Resolution](https://mlsanity.com/paper/1812.02898/) (2018)
- [Recurrent Back-Projection Network for Video Super-Resolution](https://mlsanity.com/paper/1903.10128/) (2019)
- [Video Super-Resolution with Recurrent Structure-Detail Network](https://mlsanity.com/paper/2008.00455/) (2020)
- [Revisiting Temporal Modeling for Video Super-resolution](https://mlsanity.com/paper/2008.05765/) (2020)
- [Deep Blind Video Super-resolution](https://mlsanity.com/paper/2003.04716/) (2020)
- [Deep Video Super-Resolution using HR Optical Flow Estimation](https://mlsanity.com/paper/2001.02129/) (2020)
- [iSeeBetter: Spatio-temporal video super-resolution using recurrent generative back-projection networks](https://mlsanity.com/paper/2006.11161/) (2020)
- [Towards True Detail Restoration for Super-Resolution: A Benchmark and a Quality Metric](https://mlsanity.com/paper/2203.08923/) (2022)
- [Resampling detection of recompressed images via dual-stream convolutional neural network](https://mlsanity.com/paper/1901.04637/) (2019)

## Abstract (arXiv)

Upscaled video detection is a helpful tool in multimedia forensics, but it is a challenging task that involves various upscaling and compression algorithms. There are many resolution-enhancement methods, including interpolation and deep-learning-based super-resolution, and they leave unique traces. In this work, we propose a new upscaled-resolution-detection method based on learning of visual representations using contrastive and cross-entropy losses. To explain how the method detects videos, we systematically review the major components of our framework - in particular, we show that most data-augmentation approaches hinder the learning of the method. Through extensive experiments on various datasets, we demonstrate that our method effectively detects upscaling even in compressed videos and outperforms the state-of-the-art alternatives. The code and models are publicly available at https://github.com/msu-video-group/SRDM