# FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits

arXiv: https://arxiv.org/abs/2304.10306 · HTML: https://mlsanity.com/paper/2304.10306/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Early exit and edge inference, one of 12 directions in Efficient LLM inference and serving.
- Builds on 67 of its 94 references that are in the map.
- First posted on arXiv 20 Apr 2023.

## Placed in

- Efficient LLM inference and serving / [Early exit and edge inference](https://mlsanity.com/inference/early-exit-and-edge-inference/)

## Builds on (most cited first, 30 of 67)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Perceptual Losses for Real-Time Style Transfer and Super-Resolution](https://mlsanity.com/paper/1603.08155/) (2016)
- [Billion-scale similarity search with GPUs](https://mlsanity.com/paper/1702.08734/) (2017)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Generative Adversarial Text to Image Synthesis](https://mlsanity.com/paper/1605.05396/) (2016)
- [BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks](https://mlsanity.com/paper/1709.01686/) (2017)
- [Conditional Image Synthesis With Auxiliary Classifier GANs](https://mlsanity.com/paper/1610.09585/) (2016)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Learning an Animatable Detailed 3D Face Model from In-The-Wild Images](https://mlsanity.com/paper/2012.04012/) (2020)
- [Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modeling](https://mlsanity.com/paper/2111.03930/) (2021)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Few-Shot Adversarial Learning of Realistic Neural Talking Head Models](https://mlsanity.com/paper/1905.08233/) (2019)
- [BERT Loses Patience: Fast and Robust Inference with Early Exit](https://mlsanity.com/paper/2006.04152/) (2020)
- [Depth-Adaptive Transformer](https://mlsanity.com/paper/1910.10073/) (2019)
- [I M Avatar: Implicit Morphable Head Avatars from Videos](https://mlsanity.com/paper/2112.07471/) (2021)
- [Neural Head Avatars from Monocular RGB Videos](https://mlsanity.com/paper/2112.01554/) (2021)
- [ARCH++: Animation-Ready Clothed Human Reconstruction Revisited](https://mlsanity.com/paper/2108.07845/) (2021)
- [Adaptive Neural Networks for Efficient Inference](https://mlsanity.com/paper/1702.07811/) (2017)

## Built on by (most cited first, 3 of 3)

- [Jointly-Learned Exit and Inference for a Dynamic Neural Network : JEI-DNN](https://mlsanity.com/paper/2310.09163/) (2023)
- [Conditional computation in neural networks: principles and research trends](https://mlsanity.com/paper/2403.07965/) (2024)
- [A Survey on Dynamic Neural Networks: from Computer Vision to Multi-modal Sensor Fusion](https://mlsanity.com/paper/2501.07451/) (2025)

## Abstract (arXiv)

Generative DNNs are a powerful tool for image synthesis, but they are limited by their computational load. On the other hand, given a trained model and a task, e.g. faces generation within a range of characteristics, the output image quality will be unevenly distributed among images with different characteristics. It follows, that we might restrain the models complexity on some instances, maintaining a high quality. We propose a method for diminishing computations by adding so-called early exit branches to the original architecture, and dynamically switching the computational path depending on how difficult it will be to render the output. We apply our method on two different SOTA models performing generative tasks: generation from a semantic map, and cross-reenactment of face expressions; showing it is able to output images with custom lower-quality thresholds. For a threshold of LPIPS <=0.1, we diminish their computations by up to a half. This is especially relevant for real-time applications such as synthesis of faces, when quality loss needs to be contained, but most of the inputs need fewer computations than the complex instances.