Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator

• URL: http://arxiv.org/abs/2503.01103v1
• Date: Mon, 03 Mar 2025 02:06:22 GMT
• Title: Direct Discriminative Optimization: Your Likelihood-Based Visual Generative Model is Secretly a GAN Discriminator
• Authors: Kaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He, Ming-Yu Liu, Jun Zhu, Qinsheng Zhang,
• Abstract summary: We propose a unified framework that bridges likelihood-based generative training and the maximum likelihood estimation objective.<n>Our key insight is to parameterize a discriminator implicitly using the likelihood ratio between a learnable target model and a fixed reference model.<n>Unlike GANs, this parameterization eliminates the need for joint training of generator and discriminator networks.
• Score: 38.883123034958935
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective inherently suffers from a mode-covering tendency that limits the generation quality under limited model capacity. In this work, we propose Direct Discriminative Optimization (DDO) as a unified framework that bridges likelihood-based generative training and the GAN objective to bypass this fundamental constraint. Our key insight is to parameterize a discriminator implicitly using the likelihood ratio between a learnable target model and a fixed reference model, drawing parallels with the philosophy of Direct Preference Optimization (DPO). Unlike GANs, this parameterization eliminates the need for joint training of generator and discriminator networks, allowing for direct, efficient, and effective finetuning of a well-trained model to its full potential beyond the limits of MLE. DDO can be performed iteratively in a self-play manner for progressive model refinement, with each round requiring less than 1% of pretraining epochs. Our experiments demonstrate the effectiveness of DDO by significantly advancing the previous SOTA diffusion model EDM, reducing FID scores from 1.79/1.58 to new records of 1.30/0.97 on CIFAR-10/ImageNet-64 datasets, and by consistently improving both guidance-free and CFG-enhanced FIDs of visual autoregressive models on ImageNet 256$\times$256.

Related papers

• Divergence Minimization Preference Optimization for Diffusion Model Alignment [58.651951388346525]
  Divergence Minimization Preference Optimization (DMPO) is a principled method for aligning diffusion models by minimizing reverse KL divergence.<n>Our results show that diffusion models fine-tuned with DMPO can consistently outperform or match existing techniques.<n>DMPO unlocks a robust and elegant pathway for preference alignment, bridging principled theory with practical performance in diffusion models.
  arXiv  Detail & Related papers  (2025-07-10T07:57:30Z)
• Scaling Transformers for Discriminative Recommendation via Generative Pretraining [15.796591192359044]
  We propose a framework named GPSD (textbfGenerative textbfPretraining for textbfScalable textbfDiscriminative Recommendation) to address the overfitting issue.<n>Extensive experiments conducted on both industrial-scale and publicly available datasets demonstrate the superior performance of GPSD.
  arXiv  Detail & Related papers  (2025-06-04T08:31:33Z)
• Self-NPO: Negative Preference Optimization of Diffusion Models by Simply Learning from Itself without Explicit Preference Annotations [60.143658714894336]
  Diffusion models have demonstrated remarkable success in various visual generation tasks, including image, video, and 3D content generation.<n> Preference optimization (PO) is a prominent and growing area of research that aims to align these models with human preferences.<n>We introduce Self-NPO, a Negative Preference Optimization approach that learns exclusively from the model itself.
  arXiv  Detail & Related papers  (2025-05-17T01:03:46Z)
• InPO: Inversion Preference Optimization with Reparametrized DDIM for Efficient Diffusion Model Alignment [12.823734370183482]
  We introduce DDIM-InPO, an efficient method for direct preference alignment of diffusion models. Our approach conceptualizes diffusion model as a single-step generative model, allowing us to fine-tune the outputs of specific latent variables selectively. Experimental results indicate that our DDIM-InPO achieves state-of-the-art performance with just 400 steps of fine-tuning.
  arXiv  Detail & Related papers  (2025-03-24T08:58:49Z)
• Diffusion Models without Classifier-free Guidance [41.59396565229466]
  Model-guidance (MG) is a novel objective for training diffusion model addresses and removes commonly used guidance (CFG) Our innovative approach transcends the standard modeling and incorporates the posterior probability of conditions. Our method significantly accelerates the training process, doubles inference speed, and achieve exceptional quality that parallel surpass even concurrent diffusion models with CFG.
  arXiv  Detail & Related papers  (2025-02-17T18:59:50Z)
• SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation [52.6922833948127]
  In this work, we investigate the importance of parameters in pre-trained diffusion models. We propose a novel model fine-tuning method to make full use of these ineffective parameters. Our method enhances the generative capabilities of pre-trained models in downstream applications.
  arXiv  Detail & Related papers  (2024-09-10T16:44:47Z)
• Model Inversion Attacks Through Target-Specific Conditional Diffusion Models [54.69008212790426]
  Model inversion attacks (MIAs) aim to reconstruct private images from a target classifier's training set, thereby raising privacy concerns in AI applications. Previous GAN-based MIAs tend to suffer from inferior generative fidelity due to GAN's inherent flaws and biased optimization within latent space. We propose Diffusion-based Model Inversion (Diff-MI) attacks to alleviate these issues.
  arXiv  Detail & Related papers  (2024-07-16T06:38:49Z)
• Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models [54.132297393662654]
  We introduce a hybrid method that fine-tunes cutting-edge diffusion models by optimizing reward models through RL. We demonstrate the capability of our approach to outperform the best designs in offline data, leveraging the extrapolation capabilities of reward models.
  arXiv  Detail & Related papers  (2024-05-30T03:57:29Z)
• Generative Marginalization Models [21.971818180264943]
  marginalization models (MAMs) are a new family of generative models for high-dimensional discrete data. They offer scalable and flexible generative modeling by explicitly modeling all induced marginal distributions. For energy-based training tasks, MAMs enable any-order generative modeling of high-dimensional problems beyond the scale of previous methods.
  arXiv  Detail & Related papers  (2023-10-19T17:14:29Z)
• Insights into Closed-form IPM-GAN Discriminator Guidance for Diffusion Modeling [11.68361062474064]
  We propose a theoretical framework to analyze the effect of the GAN discriminator on Langevin-based sampling.<n>We show that the proposed approach can be combined with existing accelerated-diffusion techniques to improve latent-space image generation.
  arXiv  Detail & Related papers  (2023-06-02T16:24:07Z)
• Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows [54.050498411883495]
  We develop a novel training method for generative models, such as Generative Adversarial Networks and Normalizing Flows. We show that achieving a specified precision-recall trade-off corresponds to minimizing a unique $f$-divergence from a family we call the textitPR-divergences. Our approach improves the performance of existing state-of-the-art models like BigGAN in terms of either precision or recall when tested on datasets such as ImageNet.
  arXiv  Detail & Related papers  (2023-05-30T10:07:17Z)
• RAFT: Reward rAnked FineTuning for Generative Foundation Model Alignment [32.752633250862694]
  Generative foundation models are susceptible to implicit biases that can arise from extensive unsupervised training data. We introduce a new framework, Reward rAnked FineTuning, designed to align generative models effectively.
  arXiv  Detail & Related papers  (2023-04-13T18:22:40Z)
• Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One [83.5162421521224]
  We propose a unique method termed E-ARM for training autoregressive generative models. E-ARM takes advantage of a well-designed energy-based learning objective. We show that E-ARM can be trained efficiently and is capable of alleviating the exposure bias problem.
  arXiv  Detail & Related papers  (2022-06-26T10:58:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.