# Self-Supervised GANs via Auxiliary Rotation Loss

arXiv: https://arxiv.org/abs/1811.11212 · HTML: https://mlsanity.com/paper/1811.11212/

## Key facts

- Cited by 94 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2018.

## Built on by (most cited first, 30 of 94)

- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Consistency Models](https://mlsanity.com/paper/2303.01469/) (2023)
- [MaxViT: Multi-Axis Vision Transformer](https://mlsanity.com/paper/2204.01697/) (2022)
- [Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models](https://mlsanity.com/paper/2103.04922/) (2021)
- [Co2L: Contrastive Continual Learning](https://mlsanity.com/paper/2106.14413/) (2021)
- [A Survey on Self-supervised Learning: Algorithms, Applications, and Future Trends](https://mlsanity.com/paper/2301.05712/) (2023)
- [Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection](https://mlsanity.com/paper/2203.12208/) (2022)
- [Towards Faster and Stabilized GAN Training for High-fidelity Few-shot Image Synthesis](https://mlsanity.com/paper/2101.04775/) (2021)
- [Towards Discovery and Attribution of Open-world GAN Generated Images](https://mlsanity.com/paper/2105.04580/) (2021)
- [Improved Transformer for High-Resolution GANs](https://mlsanity.com/paper/2106.07631/) (2021)
- [Data-Efficient Instance Generation from Instance Discrimination](https://mlsanity.com/paper/2106.04566/) (2021)
- [Semi-Supervised and Unsupervised Deep Visual Learning: A Survey](https://mlsanity.com/paper/2208.11296/) (2022)
- [Deepfake Network Architecture Attribution](https://mlsanity.com/paper/2202.13843/) (2022)
- [DU-GAN: Generative Adversarial Networks with Dual-Domain U-Net Based Discriminators for Low-Dose CT Denoising](https://mlsanity.com/paper/2108.10772/) (2021)
- [Training GANs with Stronger Augmentations via Contrastive Discriminator](https://mlsanity.com/paper/2103.09742/) (2021)
- [QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation](https://mlsanity.com/paper/2203.08483/) (2022)
- [Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Training](https://mlsanity.com/paper/2305.13689/) (2023)
- [StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis](https://mlsanity.com/paper/2206.09479/) (2022)
- [Self-Guided Diffusion Models](https://mlsanity.com/paper/2210.06462/) (2022)
- [Dual Contrastive Loss and Attention for GANs](https://mlsanity.com/paper/2103.16748/) (2021)
- [Continual Learning on Noisy Data Streams via Self-Purified Replay](https://mlsanity.com/paper/2110.07735/) (2021)
- [Data-Efficient GAN Training Beyond (Just) Augmentations: A Lottery Ticket Perspective](https://mlsanity.com/paper/2103.00397/) (2021)
- [Self-supervised remote sensing feature learning: Learning Paradigms, Challenges, and Future Works](https://mlsanity.com/paper/2211.08129/) (2022)
- [SSTN: Self-Supervised Domain Adaptation Thermal Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.03150/) (2021)
- [Conditional GANs with Auxiliary Discriminative Classifier](https://mlsanity.com/paper/2107.10060/) (2021)
- [Improving GANs with A Dynamic Discriminator](https://mlsanity.com/paper/2209.09897/) (2022)
- [From Google Gemini to OpenAI Q* (Q-Star): A Survey of Reshaping the Generative Artificial Intelligence (AI) Research Landscape](https://mlsanity.com/paper/2312.10868/) (2023)
- [Quaternion Generative Adversarial Networks](https://mlsanity.com/paper/2104.09630/) (2021)
- [SIRST-5K: Exploring Massive Negatives Synthesis with Self-supervised Learning for Robust Infrared Small Target Detection](https://mlsanity.com/paper/2403.05416/) (2024)
- [A Style-aware Discriminator for Controllable Image Translation](https://mlsanity.com/paper/2203.15375/) (2022)

## Abstract (arXiv)

Conditional GANs are at the forefront of natural image synthesis. The main drawback of such models is the necessity for labeled data. In this work we exploit two popular unsupervised learning techniques, adversarial training and self-supervision, and take a step towards bridging the gap between conditional and unconditional GANs. In particular, we allow the networks to collaborate on the task of representation learning, while being adversarial with respect to the classic GAN game. The role of self-supervision is to encourage the discriminator to learn meaningful feature representations which are not forgotten during training. We test empirically both the quality of the learned image representations, and the quality of the synthesized images. Under the same conditions, the self-supervised GAN attains a similar performance to state-of-the-art conditional counterparts. Finally, we show that this approach to fully unsupervised learning can be scaled to attain an FID of 23.4 on unconditional ImageNet generation.