Trending

Bookmarks

Keep Up With Latest Trending Papers. Computer Science, AI and more.Subscribe

Computer Vision

Generative ViT and Hybrid ViT

Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model

We introduce a new generative model called generative vision transformer (genvit), and extend it to hybrid discriminative-generative-modeling (hybrid discriminative-generative-modeling).

Our work is among the first to explore a single vit for image generation and classification jointly.

We conduct a series of experiments to analyze the performance of proposed models and demonstrate their superiority over prior state-of-the-arts in both generative and discriminative tasks.

Authors

Xiulong Yang, Sheng-Min Shih, Yinlin Fu, Xiaoting Zhao, Shihao Ji

Related Topics

Generative model

Vision transformer (vit)

Vit architecture

Hybrid discriminative-generative modeling

Diffusion denoising probability models

Read the Paper

Read Paper

Trending

Bookmarks

Generative ViT and Hybrid ViT - 42Papers

◐ Latest Activity

More

◐ Recommended Follows

Mary Anne Smart

More

Read Related Papers

Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes

A generative adversarial network for style augmentation for nuclei segmentation

Temporal Modeling via Video Transformer and Masked Visual-token Modeling

A generative adversarial network based image transformation policy for visual self-supervision

RegionCL: Can Simple Region Swapping Contribute to Contrastive Learning?

Learning Event-Based Models via Knowledge Distillation

A Unified Approach to Variational Autoencoders and Stochastic Normalizing Flows via Markov Chains

A Method for Evaluating the Capacity of Generative Adversarial Networks to Reproduce High-order Spatial Context

PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers

NÜWA: Visual Synthesis Pre-training for Neural visUal World creAtion