mlsanityData to 14 Oct 2026

US-GAN: On the importance of Ultimate Skip Connection for Facial Expression Synthesis

arXiv 2112.13002 ↗First posted 24 Dec 2021cs.CV eess.IVcited by 4

Not on the map. Why?

Abstract (arXiv)

We demonstrate the benefit of using an ultimate skip (US) connection for facial expression synthesis using generative adversarial networks (GAN). A direct connection transfers identity, facial, and color details from input to output while suppressing artifacts. The intermediate layers can therefore focus on expression generation only. This leads to a light-weight US-GAN model comprised of encoding layers, a single residual block, decoding layers, and an ultimate skip connection from input to output. US-GAN has 3× fewer parameters than state-of-the-art models and is trained on 2 orders of magnitude smaller dataset. It yields 7% increase in face verification score (FVS) and 27% decrease in average content distance (ACD). Based on a randomized user-study, US-GAN outperforms the state of the art by 25% in face realism, 43% in expression quality, and 58% in identity preservation.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 44 references that are in the map. First posted on arXiv 24 Dec 2021.

Builds on

23 of 44 references.

References · 23

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
  4. 2016Densely Connected Convolutional Networkscited by 6,720
  5. 2016Image-to-Image Translation with Conditional Adversarial Networkscited by 4,527
  6. 2016Perceptual Losses for Real-Time Style Transfer and Super-Resolutioncited by 2,694
  7. 2014Conditional Generative Adversarial Netscited by 2,162
  8. 2016Instance Normalization: The Missing Ingredient for Fast Stylizationcited by 1,198
  9. 2017StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translationcited by 1,039
  10. 2017Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networkscited by 707
  11. 2017AffectNet: A Database for Facial Expression, Valence, and Arousal Computing in the Wildcited by 492
  12. 2017DualGAN: Unsupervised Dual Learning for Image-to-Image Translationcited by 310
11 more
  1. 2017FSRNet: End-to-End Learning Face Super-Resolution with Facial Priorscited by 170
  2. 2019STGAN: A Unified Selective Transfer Network for Arbitrary Image Attribute Editingcited by 120
  3. 2016Invertible Conditional GANs for image editingcited by 118
  4. 2019RelGAN: Multi-Domain Image-to-Image Translation via Relative Attributescited by 56
  5. 2020Learning Spatial Attention for Face Super-Resolutioncited by 55
  6. 2017ExprGAN: Facial Expression Editing with Controllable Expression Intensitycited by 47
  7. 2020Cascade EF-GAN: Progressive Facial Expression Editing with Local Focusescited by 43
  8. 2016Learning Residual Images for Face Attribute Manipulationcited by 40
  9. 2021High-Fidelity and Arbitrary Face Editingcited by 35
  10. 2020Pixel-based Facial Expression Synthesiscited by 3
  11. 2020Masked Linear Regression for Learning Local Receptive Fields for Facial Expression Synthesiscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 2; 2025: 0; 2026: 1.

4 papers.

  1. 2024A Review of Human Emotion Synthesis Based on Generative Technologycited by 7
  2. 2022Facial Expression Video Generation Based-On Spatio-temporal Convolutional GAN: FEV-GANcited by 4
  3. 2024FacEnhance: Facial Expression Enhancing with Recurrent DDPMscited by 1
  4. 2026Improving Generative Adversarial Network Generalization for Facial Expression Synthesiscited by 0