mlsanityData to 14 Oct 2026

Mitigating Exposure Bias in Discriminator Guided Diffusion Models

arXiv 2311.11164 ↗First posted 18 Nov 2023cs.CV cs.AI cs.LGcited by 2

On the map: Diffusion models → Diffusion foundations and sampling

Abstract (arXiv)

Diffusion Models have demonstrated remarkable performance in image generation. However, their demanding computational requirements for training have prompted ongoing efforts to enhance the quality of generated images through modifications in the sampling process. A recent approach, known as Discriminator Guidance, seeks to bridge the gap between the model score and the data score by incorporating an auxiliary term, derived from a discriminator network. We show that despite significantly improving sample quality, this technique has not resolved the persistent issue of Exposure Bias and we propose SEDM-G++, which incorporates a modified sampling approach, combining Discriminator Guidance and Epsilon Scaling. Our proposed approach outperforms the current state-of-the-art, by achieving an FID score of 1.73 on the unconditional CIFAR-10 dataset.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Diffusion foundations and sampling, one of 14 directions in Diffusion models. Builds on 46 of its 49 references that are in the map. First posted on arXiv 18 Nov 2023.

Builds on

46 of 49 references.

Closest ancestors · 25

Same direction, newest first

  1. 2023Elucidating the Exposure Bias in Diffusion Models29 Aug
  2. 2023Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps24 May
  3. 2023Input Perturbation Reduces Exposure Bias in Diffusion Models27 Jan
  4. 2022Refining Generative Process with Discriminator Guidance in Score-based Diffusion Models28 Nov
  5. 2022On Distillation of Guided Diffusion Models6 Oct
  6. 2022Estimating the Optimal Covariance with Imperfect Mean in Diffusion Probabilistic Models15 Jun
  7. 2022Elucidating the Design Space of Diffusion-Based Generative Models1 Jun
  8. 2022Maximum Likelihood Training of Implicit Nonlinear Diffusion Models27 May
  9. 2022Subspace Diffusion Generative Models3 May
  10. 2022Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models17 Jan
  11. 2021High-Resolution Image Synthesis with Latent Diffusion Models20 Dec
  12. 2021Tackling the Generative Learning Trilemma with Denoising Diffusion GANs15 Dec
13 more
  1. 2021Score-Based Generative Modeling with Critically-Damped Langevin Diffusion14 Dec
  2. 2021Diffusion Autoencoders: Toward a Meaningful and Decodable Representation30 Nov
  3. 2021Vector Quantized Diffusion Model for Text-to-Image Synthesis29 Nov
  4. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes24 Nov
  5. 2021ILVR: Conditioning Method for Denoising Diffusion Probabilistic Models6 Aug
  6. 2021Variational Diffusion Models1 Jul
  7. 2021Score-based Generative Modeling in Latent Space10 Jun
  8. 2021Soft Truncation: A Universal Training Technique of Score-based Diffusion Model for High Precision Score Estimation10 Jun
  9. 2021Diffusion Models Beat GANs on Image Synthesis11 May
  10. 2021Improved Denoising Diffusion Probabilistic Models18 Feb
  11. 2020Score-Based Generative Modeling through Stochastic Differential Equations26 Nov
  12. 2020Denoising Diffusion Implicit Models6 Oct
  13. 2020Denoising Diffusion Probabilistic Models19 Jun

Other references · 21

  1. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  2. 2019Generative Modeling by Estimating Gradients of the Data Distributioncited by 4,101
  3. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  4. 2022Video Diffusion Modelscited by 2,305
  5. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,476
  6. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,430
  7. 2020DiffWave: A Versatile Diffusion Model for Audio Synthesiscited by 1,354
  8. 2022Null-text Inversion for Editing Real Images using Guided Diffusion Modelscited by 1,179
  9. 2022Imagic: Text-Based Real Image Editing with Diffusion Modelscited by 1,178
  10. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 927
  11. 2021Diffusion Probabilistic Models for 3D Point Cloud Generationcited by 735
  12. 2022Compositional Visual Generation with Composable Diffusion Modelscited by 624
9 more
  1. 2020WaveGrad: Estimating Gradients for Waveform Generationcited by 622
  2. 2015Sequence Level Training with Recurrent Neural Networkscited by 576
  3. 20213D Shape Generation and Completion through Point-Voxel Diffusioncited by 516
  4. 2022MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolationcited by 309
  5. 2021Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems through Stochastic Contractioncited by 307
  6. 2022Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpaintingcited by 233
  7. 2023Implicit Diffusion Models for Continuous Super-Resolutioncited by 218
  8. 2022Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decodingcited by 144
  9. 2019Generalization in Generation: A closer look at Exposure Biascited by 123

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025FEB-Cache: Frequency-Guided Exposure Bias Reduction for Enhancing Diffusion Transformer Cachingcited by 2
  2. 2025Improving Discriminator Guidance in Diffusion Modelscited by 2

Similar, not cited

Close in wording, no citation either way

  1. 2025Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correction
  2. 2023Elucidating The Design Space of Classifier-Guided Diffusion Generation
  3. 2023Unmasking Bias in Diffusion Model Training
  4. 2022Improving Sample Quality of Diffusion Models Using Self-Attention Guidance
  5. 2024Diffusion Models Need Visual Priors for Image Generation
  6. 2023Masked Diffusion Models Are Fast Distribution Learners
  7. 2024Plug-and-Play Diffusion Distillation
  8. 2026Revisiting Classifier-Free Guidance Methods in Latent Diffusion Models