mlsanityData to 14 Oct 2026

Deep Feature Interpolation for Image Content Changes

arXiv 1611.05507 ↗First posted 16 Nov 2016cs.CVcited by 80

Not on the map. Why?

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.

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

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 20; 2022: 23; 2023: 13; 2024: 11; 2025: 12; 2026: 1.

80 papers.

Sort:

By area:

  1. 2024Improving Alignment and Robustness with Circuit Breakerscited by 322
  2. 2025AxBench: Steering LLMs? Even Simple Baselines Outperform Sparse Autoencoderscited by 218
  3. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 205
  4. 2023Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion modelscited by 205
  5. 2023A Complete Survey on Generative AI (AIGC): Is ChatGPT from GPT-4 to GPT-5 All You Need?cited by 84
  6. 2024Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categoriescited by 77
  7. 2021Differentiable Quality Diversitycited by 72
  8. 2021A Latent Transformer for Disentangled Face Editing in Images and Videoscited by 67
  9. 2021Transferable Semantic Augmentation for Domain Adaptationcited by 56
  10. 2022Spectral Feature Augmentation for Graph Contrastive Learning and Beyondcited by 49
  11. 2023NoiseCLR: A Contrastive Learning Approach for Unsupervised Discovery of Interpretable Directions in Diffusion Modelscited by 47
  12. 2025CO-SPY: Combining Semantic and Pixel Features to Detect Synthetic Images by AIcited by 42
38 more
  1. 2025Enhancing Automated Interpretability with Output-Centric Feature Descriptionscited by 41
  2. 2021StyleMC: Multi-Channel Based Fast Text-Guided Image Generation and Manipulationcited by 40
  3. 2021CoReD: Generalizing Fake Media Detection with Continual Representation using Distillationcited by 37
  4. 2022Implicit Sample Extension for Unsupervised Person Re-Identificationcited by 31
  5. 2022ReMix: A General and Efficient Framework for Multiple Instance Learning based Whole Slide Image Classificationcited by 30
  6. 2023RadEdit: stress-testing biomedical vision models via diffusion image editingcited by 28
  7. 2021CoMoGAN: continuous model-guided image-to-image translationcited by 27
  8. 2021Do Not Escape From the Manifold: Discovering the Local Coordinates on the Latent Space of GANscited by 26
  9. 2022You Only Cut Once: Boosting Data Augmentation with a Single Cutcited by 22
  10. 2022Controllable Data Generation by Deep Learning: A Reviewcited by 20
  11. 2023Learning to Extrapolate: A Transductive Approachcited by 19
  12. 2022AdaFocusV3: On Unified Spatial-temporal Dynamic Video Recognitioncited by 18
  13. 2021PU-Flow: a Point Cloud Upsampling Network with Normalizing Flowscited by 17
  14. 2022Towards better understanding and better generalization of few-shot classification in histology images with contrastive learningcited by 16
  15. 2022GAN-based Facial Attribute Manipulationcited by 16
  16. 2024HiddenGuard: Fine-Grained Safe Generation with Specialized Representation Routercited by 16
  17. 2021Behavior-Driven Synthesis of Human Dynamicscited by 14
  18. 2022FAKD: Feature Augmented Knowledge Distillation for Semantic Segmentationcited by 14
  19. 2021DeepBlur: A Simple and Effective Method for Natural Image Obfuscationcited by 13
  20. 2021Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulationcited by 13
  21. 2022Portrait Eyeglasses and Shadow Removal by Leveraging 3D Synthetic Datacited by 11
  22. 2022Exploring Gradient-based Multi-directional Controls in GANscited by 10
  23. 2023Spatially Covariant Lesion Segmentationcited by 10
  24. 2021DEX: Domain Embedding Expansion for Generalized Person Re-identificationcited by 8
  25. 2023Conservative Prediction via Data-Driven Confidence Minimizationcited by 8
  26. 2021Inverting Adversarially Robust Networks for Image Synthesiscited by 6
  27. 2021FreeStyleGAN: Free-view Editable Portrait Rendering with the Camera Manifoldcited by 6
  28. 2023Non-exemplar Class-incremental Learning by Random Auxiliary Classes Augmentation and Mixed Featurescited by 6
  29. 2021NeRD: Neural Representation of Distribution for Medical Image Segmentationcited by 5
  30. 2024BSDA: Bayesian Random Semantic Data Augmentation for Medical Image Classificationcited by 5
  31. 2024Going beyond Compositions, DDPMs Can Produce Zero-Shot Interpolationscited by 5
  32. 2022Vec2Face-v2: Unveil Human Faces from their Blackbox Features via Attention-based Network in Face Recognitioncited by 4
  33. 2023Learning Iterative Neural Optimizers for Image Steganographycited by 4
  34. 2024What Has Been Overlooked in Contrastive Source-Free Domain Adaptation: Leveraging Source-Informed Latent Augmentation within Neighborhood Contextcited by 4
  35. 2021Heredity-aware Child Face Image Generation with Latent Space Disentanglementcited by 3
  36. 2022A comprehensive survey on semantic facial attribute editing using generative adversarial networkscited by 3
  37. 2022Analyzing the Latent Space of GAN through Local Dimension Estimationcited by 3
  38. 2024A Unified Deep Semantic Expansion Framework for Domain-Generalized Person Re-identificationcited by 3

50 most cited of 80 All 80 (JSON)