# Transformation Consistency Regularization- A Semi-Supervised Paradigm for Image-to-Image Translation

arXiv: https://arxiv.org/abs/2007.07867 · HTML: https://mlsanity.com/paper/2007.07867/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 22 of 22)

- [Image-to-Image Translation: Methods and Applications](https://mlsanity.com/paper/2101.08629/) (2021)
- [Exploiting Transformation Invariance and Equivariance for Self-supervised Sound Localisation](https://mlsanity.com/paper/2206.12772/) (2022)
- [Revisiting Consistency Regularization for Semi-supervised Change Detection in Remote Sensing Images](https://mlsanity.com/paper/2204.08454/) (2022)
- [Few-shot Open-set Recognition by Transformation Consistency](https://mlsanity.com/paper/2103.01537/) (2021)
- [Beyond Augmentation: Empowering Model Robustness under Extreme Capture Environments](https://mlsanity.com/paper/2407.13640/) (2024)
- [Training a Task-Specific Image Reconstruction Loss](https://mlsanity.com/paper/2103.14616/) (2021)
- [FreeCompose: Generic Zero-Shot Image Composition with Diffusion Prior](https://mlsanity.com/paper/2407.04947/) (2024)
- [Multi-Source domain adaptation via supervised contrastive learning and confident consistency regularization](https://mlsanity.com/paper/2106.16093/) (2021)
- [Optimal Transport-Guided Conditional Score-Based Diffusion Models](https://mlsanity.com/paper/2311.01226/) (2023)
- [Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation](https://mlsanity.com/paper/2203.12707/) (2022)
- [Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach](https://mlsanity.com/paper/2401.09671/) (2024)
- [Semi-supervision semantic segmentation with uncertainty-guided self cross supervision](https://mlsanity.com/paper/2203.05118/) (2022)
- [Feedback Schr"odinger Bridge Matching](https://mlsanity.com/paper/2410.14055/) (2024)
- [Semi-supervised Learning for Segmentation of Bleeding Regions in Video Capsule Endoscopy](https://mlsanity.com/paper/2308.02869/) (2023)
- [Improving GAN Training via Feature Space Shrinkage](https://mlsanity.com/paper/2303.01559/) (2023)
- [AptSim2Real: Approximately-Paired Sim-to-Real Image Translation](https://mlsanity.com/paper/2303.12704/) (2023)
- [Keypoint-Guided Optimal Transport: Models, Algorithms, and Applications](https://mlsanity.com/paper/2303.13102/) (2023)
- [A Semi-Paired Approach For Label-to-Image Translation](https://mlsanity.com/paper/2306.13585/) (2023)
- [GMapLatent: Geometric Mapping in Latent Space](https://mlsanity.com/paper/2503.23407/) (2025)
- [Semi-supervised Contrastive Outlier removal for Pseudo Expectation Maximization (SCOPE)](https://mlsanity.com/paper/2206.14261/) (2022)
- [Incremental Semi-supervised Federated Learning for Health Inference via Mobile Sensing](https://mlsanity.com/paper/2312.12666/) (2023)
- [Inverse Entropic Optimal Transport Solves Semi-supervised Learning via Data Likelihood Maximization](https://mlsanity.com/paper/2410.02628/) (2024)

## Abstract (arXiv)

Scarcity of labeled data has motivated the development of semi-supervised learning methods, which learn from large portions of unlabeled data alongside a few labeled samples. Consistency Regularization between model's predictions under different input perturbations, particularly has shown to provide state-of-the art results in a semi-supervised framework. However, most of these method have been limited to classification and segmentation applications. We propose Transformation Consistency Regularization, which delves into a more challenging setting of image-to-image translation, which remains unexplored by semi-supervised algorithms. The method introduces a diverse set of geometric transformations and enforces the model's predictions for unlabeled data to be invariant to those transformations. We evaluate the efficacy of our algorithm on three different applications: image colorization, denoising and super-resolution. Our method is significantly data efficient, requiring only around 10 - 20% of labeled samples to achieve similar image reconstructions to its fully-supervised counterpart. Furthermore, we show the effectiveness of our method in video processing applications, where knowledge from a few frames can be leveraged to enhance the quality of the rest of the movie.