paper-with-me

Papers

Your ViT is Secretly a Hybrid Discriminative-Generative Diffusion Model

2022-08-16 · Xiulong Yang, Sheng-Min Shih, Yinlin Fu, Xiaoting Zhao, Shihao Ji

Diffusion Denoising Probability Models (DDPM) and Vision Transformer (ViT) have demonstrated significant progress in generative tasks and discriminative tasks, respectively, and thus far these models have largely been developed in their own domains. In this paper, we establish a direct connection between DDPM and ViT by integrating the ViT architecture into DDPM, and introduce a new generative model called Generative ViT (GenViT). The modeling flexibility of ViT enables us to further extend GenViT to hybrid discriminative-generative modeling, and introduce a Hybrid ViT (HybViT). 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. Our code and pre-trained models can be found in https://github.com/sndnyang/Diffusion_ViT .

📄 PDF Abstract BibTeX arXiv:2208.07791

Code (2)

sndnyang/Diffusion_ViT 공식 구현 pytorch
MindCode-4/code-5/tree/main/vit_hybrid mindspore

Tasks

DenoisingImage ClassificationImage Generation

Methods 이 논문이 사용한 방법론

Multi-Head Attention 설명 없음
Attention 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Absolute Position Encodings Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Position-Wise Feed-Forward Layer 설명 없음
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Residual Connection 설명 없음

Similar Papers 제목 키워드 기반

Your Diffusion Model is Secretly a Zero-Shot Classifier

2023-03-28 · ICCV 2023 1 · Alexander C. Li, Mihir Prabhudesai, Shivam Duggal, Ellis Brown 외

The recent wave of large-scale text-to-image diffusion models has dramatically increased our text-based image generation abilities. These models can generate realistic images for a staggering variety of prompts and exhib…

Domain GeneralizationFine-Grained Image ClassificationImage ClassificationImage Generation+5

Your Classifier is Secretly an Energy Based Model and You Should Treat it Like One

2019-12-06 · ICLR 2020 1 · Will Grathwohl, Kuan-Chieh Wang, Jörn-Henrik Jacobsen, David Duvenaud 외

We propose to reinterpret a standard discriminative classifier of p(y|x) as an energy based model for the joint distribution p(x,y). In this setting, the standard class probabilities can be easily computed as well as unn…

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

2025-03-03 · Kaiwen Zheng, Yongxin Chen, Huayu Chen, Guande He 외

While likelihood-based generative models, particularly diffusion and autoregressive models, have achieved remarkable fidelity in visual generation, the maximum likelihood estimation (MLE) objective, which minimizes the f…

Image Generation

Your VAR Model is Secretly an Efficient and Explainable Generative Classifier

2025-10-14 · Yi-Chung Chen, David I. Inouye, Jing Gao arxiv

Generative classifiers, which leverage conditional generative models for classification, have recently demonstrated desirable properties such as robustness to distribution shifts. However, recent progress in this area ha…

class-incremental learning

Your Image is Secretly the Last Frame of a Pseudo Video

2024-10-26 · Wenlong Chen, Wenlin Chen, Lapo Rastrelli, Yingzhen Li

Diffusion models, which can be viewed as a special case of hierarchical variational autoencoders (HVAEs), have shown profound success in generating photo-realistic images. In contrast, standard HVAEs often produce images…

Data AugmentationImage Generation