Image de couverture de livre

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

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Zheng, Kaiwen, Chen, Yongxin, Chen, Huayu, He, Guande, Liu, Ming-Yu, Zhu, Jun, Zhang, Qinsheng
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Consistency Diffusion Bridge Models
par: He, Guande, et autres
Publié: (2024)

DGL-GAN: Discriminator Guided Learning for GAN Compression
par: Tian, Yuesong, et autres
Publié: (2021)

Elucidating the Preconditioning in Consistency Distillation
par: Zheng, Kaiwen, et autres
Publié: (2025)

Visual Generation Without Guidance
par: Chen, Huayu, et autres
Publié: (2025)

Large Scale Diffusion Distillation via Score-Regularized Continuous-Time Consistency
par: Zheng, Kaiwen, et autres
Publié: (2025)

RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
par: Fan, Jiaojiao, et autres
Publié: (2024)

Discriminator-Free Direct Preference Optimization for Video Diffusion
par: Cheng, Haoran, et autres
Publié: (2025)

Masked Diffusion Models are Secretly Time-Agnostic Masked Models and Exploit Inaccurate Categorical Sampling
par: Zheng, Kaiwen, et autres
Publié: (2024)

Underwater Image Reconstruction Using a Swin Transformer-Based Generator and PatchGAN Discriminator
par: Akash, Md. Mahbub Hasan, et autres
Publié: (2025)

Bridging Generative and Discriminative Models for Unified Visual Perception with Diffusion Priors
par: Dong, Shiyin, et autres
Publié: (2024)

DiffusionNFT: Online Diffusion Reinforcement with Forward Process
par: Zheng, Kaiwen, et autres
Publié: (2025)

Few-shot Image Generation via Masked Discrimination
par: Zhu, Jingyuan, et autres
Publié: (2022)

PurifyGen: A Risk-Discrimination and Semantic-Purification Model for Safe Text-to-Image Generation
par: Cao, Zongsheng, et autres
Publié: (2025)

Insights into Closed-form IPM-GAN Discriminator Guidance for Diffusion Modeling
par: Srikanth, Aadithya, et autres
Publié: (2023)

Direct Ascent Synthesis: Revealing Hidden Generative Capabilities in Discriminative Models
par: Fort, Stanislav, et autres
Publié: (2025)

Adaptive Discriminative Regularization for Visual Classification
par: Zhao, Qingsong, et autres
Publié: (2022)

Aligning Generative Denoising with Discriminative Objectives Unleashes Diffusion for Visual Perception
par: Pang, Ziqi, et autres
Publié: (2025)

Discriminative Image Generation with Diffusion Models for Zero-Shot Learning
par: Fu, Dingjie, et autres
Publié: (2024)

Vidu: a Highly Consistent, Dynamic and Skilled Text-to-Video Generator with Diffusion Models
par: Bao, Fan, et autres
Publié: (2024)

GAN with Skip Patch Discriminator for Biological Electron Microscopy Image Generation
par: Roy, Nishith Ranjon, et autres
Publié: (2024)

UniGenDet: A Unified Generative-Discriminative Framework for Co-Evolutionary Image Generation and Generated Image Detection
par: Zhang, Yanran, et autres
Publié: (2026)

Your Diffusion Model is Secretly a Certifiably Robust Classifier
par: Chen, Huanran, et autres
Publié: (2024)

Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulation
par: Liu, Fengbei, et autres
Publié: (2023)

PUGAN: Physical Model-Guided Underwater Image Enhancement Using GAN with Dual-Discriminators
par: Cong, Runmin, et autres
Publié: (2023)

Dynamically Masked Discriminator for Generative Adversarial Networks
par: Zhang, Wentian, et autres
Publié: (2023)

Correlative and Discriminative Label Grouping for Multi-Label Visual Prompt Tuning
par: Ma, LeiLei, et autres
Publié: (2025)

RAD-2: Scaling Reinforcement Learning in a Generator-Discriminator Framework
par: Gao, Hao, et autres
Publié: (2026)

Learning Discriminative Features for Crowd Counting
par: Chen, Yuehai, et autres
Publié: (2023)

RIFLEx: A Free Lunch for Length Extrapolation in Video Diffusion Transformers
par: Zhao, Min, et autres
Publié: (2025)

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment
par: Chen, Huayu, et autres
Publié: (2024)

Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
par: Wang, Changwei, et autres
Publié: (2025)

minWM: A Full-Stack Open-Source Framework for Real-Time Interactive Video World Models
par: Zhao, Min, et autres
Publié: (2026)

Multimodal Feature Prototype Learning for Interpretable and Discriminative Cancer Survival Prediction
par: Jiang, Shuo, et autres
Publié: (2025)

Improving Visual Discriminability of CLIP for Training-Free Open-Vocabulary Semantic Segmentation
par: Zhou, Jinxin, et autres
Publié: (2025)

Fake it till You Make it: Reward Modeling as Discriminative Prediction
par: Liu, Runtao, et autres
Publié: (2025)

Continual Action Assessment via Task-Consistent Score-Discriminative Feature Distribution Modeling
par: Li, Yuan-Ming, et autres
Publié: (2023)

DMOFC: Discrimination Metric-Optimized Feature Compression
par: Gao, Changsheng, et autres
Publié: (2024)

Rethinking Domain Generalization: Discriminability and Generalizability
par: Long, Shaocong, et autres
Publié: (2023)

AnomalyLMM: Bridging Generative Knowledge and Discriminative Retrieval for Text-Based Person Anomaly Search
par: Ju, Hao, et autres
Publié: (2025)

Exploiting Discriminative Codebook Prior for Autoregressive Image Generation
par: Tang, Longxiang, et autres
Publié: (2025)