# Deep Feature Interpolation for Image Content Changes

arXiv: https://arxiv.org/abs/1611.05507 · HTML: https://mlsanity.com/paper/1611.05507/

## Key facts

- Cited by 80 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Nov 2016.

## Built on by (most cited first, 30 of 80)

- [Improving Alignment and Robustness with Circuit Breakers](https://mlsanity.com/paper/2406.04313/) (2024)
- [AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoders](https://mlsanity.com/paper/2501.17148/) (2025)
- [Glaze: Protecting Artists from Style Mimicry by Text-to-Image Models](https://mlsanity.com/paper/2302.04222/) (2023)
- [Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models](https://mlsanity.com/paper/2306.04675/) (2023)
- [A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?](https://mlsanity.com/paper/2303.11717/) (2023)
- [Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories](https://mlsanity.com/paper/2406.00034/) (2024)
- [Differentiable Quality Diversity](https://mlsanity.com/paper/2106.03894/) (2021)
- [A Latent Transformer for Disentangled Face Editing in Images and Videos](https://mlsanity.com/paper/2106.11895/) (2021)
- [Transferable Semantic Augmentation for Domain Adaptation](https://mlsanity.com/paper/2103.12562/) (2021)
- [Spectral Feature Augmentation for Graph Contrastive Learning and Beyond](https://mlsanity.com/paper/2212.01026/) (2022)
- [NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Models](https://mlsanity.com/paper/2312.05390/) (2023)
- [CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AI](https://mlsanity.com/paper/2503.18286/) (2025)
- [Enhancing Automated Interpretability with Output-Centric Feature Descriptions](https://mlsanity.com/paper/2501.08319/) (2025)
- [StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulation](https://mlsanity.com/paper/2112.08493/) (2021)
- [CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation](https://mlsanity.com/paper/2107.02408/) (2021)
- [Implicit Sample Extension for Unsupervised Person Re-Identification](https://mlsanity.com/paper/2204.06892/) (2022)
- [ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classification](https://mlsanity.com/paper/2207.01805/) (2022)
- [RadEdit: stress-testing biomedical vision models via diffusion image editing](https://mlsanity.com/paper/2312.12865/) (2023)
- [CoMoGAN: continuous model-guided image-to-image translation](https://mlsanity.com/paper/2103.06879/) (2021)
- [Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANs](https://mlsanity.com/paper/2106.06959/) (2021)
- [You Only Cut Once: Boosting Data Augmentation with a Single Cut](https://mlsanity.com/paper/2201.12078/) (2022)
- [Controllable Data Generation by Deep Learning: A Review](https://mlsanity.com/paper/2207.09542/) (2022)
- [Learning to Extrapolate: A Transductive Approach](https://mlsanity.com/paper/2304.14329/) (2023)
- [AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognition](https://mlsanity.com/paper/2209.13465/) (2022)
- [PU-Flow: a Point Cloud Upsampling Network with Normalizing Flows](https://mlsanity.com/paper/2107.05893/) (2021)
- [Towards better understanding and better generalization of few-shot classification in histology images with contrastive learning](https://mlsanity.com/paper/2202.09059/) (2022)
- [GAN-based Facial Attribute Manipulation](https://mlsanity.com/paper/2210.12683/) (2022)
- [HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Router](https://mlsanity.com/paper/2410.02684/) (2024)
- [Behavior-Driven Synthesis of Human Dynamics](https://mlsanity.com/paper/2103.04677/) (2021)
- [FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2208.14143/) (2022)

## Abstract (arXiv)

We propose Deep Feature Interpolation (DFI), a new data-driven baseline for automatic high-resolution image transformation. As the name suggests, it relies only on simple linear interpolation of deep convolutional features from pre-trained convnets. We show that despite its simplicity, DFI can perform high-level semantic transformations like "make older/younger", "make bespectacled", "add smile", among others, surprisingly well - sometimes even matching or outperforming the state-of-the-art. This is particularly unexpected as DFI requires no specialized network architecture or even any deep network to be trained for these tasks. DFI therefore can be used as a new baseline to evaluate more complex algorithms and provides a practical answer to the question of which image transformation tasks are still challenging in the rise of deep learning.