# Teachers Do More Than Teach: Compressing Image-to-Image Models

arXiv: https://arxiv.org/abs/2103.03467 · HTML: https://mlsanity.com/paper/2103.03467/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- Builds on 72 of its 88 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 30 of 72)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [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)
- [MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications](https://mlsanity.com/paper/1704.04861/) (2017)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [Large Scale GAN Training for High Fidelity Natural Image Synthesis](https://mlsanity.com/paper/1809.11096/) (2018)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [DARTS: Differentiable Architecture Search](https://mlsanity.com/paper/1806.09055/) (2018)
- [Similarity of Neural Network Representations Revisited](https://mlsanity.com/paper/1905.00414/) (2019)
- [Spectral Normalization for Generative Adversarial Networks](https://mlsanity.com/paper/1802.05957/) (2018)
- [Knowledge Distillation: A Survey](https://mlsanity.com/paper/2006.05525/) (2020)
- [Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learning](https://mlsanity.com/paper/1602.07261/) (2016)
- [Neural Architecture Search with Reinforcement Learning](https://mlsanity.com/paper/1611.01578/) (2016)
- [Semantic Image Synthesis with Spatially-Adaptive Normalization](https://mlsanity.com/paper/1903.07291/) (2019)
- [Demystifying MMD GANs](https://mlsanity.com/paper/1801.01401/) (2018)
- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs](https://mlsanity.com/paper/1711.11585/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [MnasNet: Platform-Aware Neural Architecture Search for Mobile](https://mlsanity.com/paper/1807.11626/) (2018)
- [Self-Attention Generative Adversarial Networks](https://mlsanity.com/paper/1805.08318/) (2018)
- [Once-for-All: Train One Network and Specialize it for Efficient Deployment](https://mlsanity.com/paper/1908.09791/) (2019)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Learning Efficient Convolutional Networks through Network Slimming](https://mlsanity.com/paper/1708.06519/) (2017)
- [ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware](https://mlsanity.com/paper/1812.00332/) (2018)
- [Rethinking the Value of Network Pruning](https://mlsanity.com/paper/1810.05270/) (2018)
- [FBNet: Hardware-Aware Efficient ConvNet Design via Differentiable Neural Architecture Search](https://mlsanity.com/paper/1812.03443/) (2018)

## Built on by (most cited first, 30 of 37)

- [SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds](https://mlsanity.com/paper/2306.00980/) (2023)
- [A Good Image Generator Is What You Need for High-Resolution Video Synthesis](https://mlsanity.com/paper/2104.15069/) (2021)
- [Rethinking Vision Transformers for MobileNet Size and Speed](https://mlsanity.com/paper/2212.08059/) (2022)
- [Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models](https://mlsanity.com/paper/2211.02048/) (2022)
- [MobileFaceSwap: A Lightweight Framework for Video Face Swapping](https://mlsanity.com/paper/2201.03808/) (2022)
- [Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation](https://mlsanity.com/paper/2203.06321/) (2022)
- [PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection](https://mlsanity.com/paper/2205.11098/) (2022)
- [Pruning-as-Search: Efficient Neural Architecture Search via Channel Pruning and Structural Reparameterization](https://mlsanity.com/paper/2206.01198/) (2022)
- [F8Net: Fixed-Point 8-bit Only Multiplication for Network Quantization](https://mlsanity.com/paper/2202.05239/) (2022)
- [Online Multi-Granularity Distillation for GAN Compression](https://mlsanity.com/paper/2108.06908/) (2021)
- [Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme](https://mlsanity.com/paper/2110.14439/) (2021)
- [Distilling a Powerful Student Model via Online Knowledge Distillation](https://mlsanity.com/paper/2103.14473/) (2021)
- [Fast-Vid2Vid: Spatial-Temporal Compression for Video-to-Video Synthesis](https://mlsanity.com/paper/2207.05049/) (2022)
- [Layer Freezing & Data Sieving: Missing Pieces of a Generic Framework for Sparse Training](https://mlsanity.com/paper/2209.11204/) (2022)
- [Region-aware Knowledge Distillation for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2205.12451/) (2022)
- [Learning From Biased Soft Labels](https://mlsanity.com/paper/2302.08155/) (2023)
- [Balanced Training for Sparse GANs](https://mlsanity.com/paper/2302.14670/) (2023)
- [Cut Inner Layers: A Structured Pruning Strategy for Efficient U-Net GANs](https://mlsanity.com/paper/2206.14658/) (2022)
- [Discriminator-Cooperated Feature Map Distillation for GAN Compression](https://mlsanity.com/paper/2212.14169/) (2022)
- [Enhancing Indoor Occupancy Prediction via Sparse Query-Based Multi-Level Consistent Knowledge Distillation](https://mlsanity.com/paper/2602.02318/) (2026)
- [UGC: Unified GAN Compression for Efficient Image-to-Image Translation](https://mlsanity.com/paper/2309.09310/) (2023)
- [Compressing Image-to-Image Translation GANs Using Local Density Structures on Their Learned Manifold](https://mlsanity.com/paper/2312.14776/) (2023)
- [Knowledge Distillation for Image Restoration : Simultaneous Learning from Degraded and Clean Images](https://mlsanity.com/paper/2501.09268/) (2025)
- [Information-Theoretic GAN Compression with Variational Energy-based Model](https://mlsanity.com/paper/2303.16050/) (2023)
- [Shortcut-V2V: Compression Framework for Video-to-Video Translation based on Temporal Redundancy Reduction](https://mlsanity.com/paper/2308.08011/) (2023)
- [CoroNetGAN: Controlled Pruning of GANs via Hypernetworks](https://mlsanity.com/paper/2403.08261/) (2024)
- [Soft Knowledge Distillation with Multi-Dimensional Cross-Net Attention for Image Restoration Models Compression](https://mlsanity.com/paper/2501.09321/) (2025)
- [Digital Staining with Knowledge Distillation: A Unified Framework for Unpaired and Paired-But-Misaligned Data](https://mlsanity.com/paper/2504.09899/) (2025)
- [Exploring Content Relationships for Distilling Efficient GANs](https://mlsanity.com/paper/2212.11091/) (2022)
- [Unsupervised Deep Digital Staining For Microscopic Cell Images Via Knowledge Distillation](https://mlsanity.com/paper/2303.02057/) (2023)

## Abstract (arXiv)

Generative Adversarial Networks (GANs) have achieved huge success in generating high-fidelity images, however, they suffer from low efficiency due to tremendous computational cost and bulky memory usage. Recent efforts on compression GANs show noticeable progress in obtaining smaller generators by sacrificing image quality or involving a time-consuming searching process. In this work, we aim to address these issues by introducing a teacher network that provides a search space in which efficient network architectures can be found, in addition to performing knowledge distillation. First, we revisit the search space of generative models, introducing an inception-based residual block into generators. Second, to achieve target computation cost, we propose a one-step pruning algorithm that searches a student architecture from the teacher model and substantially reduces searching cost. It requires no l1 sparsity regularization and its associated hyper-parameters, simplifying the training procedure. Finally, we propose to distill knowledge through maximizing feature similarity between teacher and student via an index named Global Kernel Alignment (GKA). Our compressed networks achieve similar or even better image fidelity (FID, mIoU) than the original models with much-reduced computational cost, e.g., MACs. Code will be released at https://github.com/snap-research/CAT.