Search Results for author: Vincent Tao Hu

Found 14 papers, 7 papers with code

Diffusion Models and Representation Learning: A Survey

1 code implementation30 Jun 2024 Michael Fuest, Pingchuan Ma, Ming Gui, Johannes S. Fischer, Vincent Tao Hu, Bjorn Ommer

Diffusion Models are popular generative modeling methods in various vision tasks, attracting significant attention.

Denoising Representation Learning +1

Continuous, Subject-Specific Attribute Control in T2I Models by Identifying Semantic Directions

1 code implementation25 Mar 2024 Stefan Andreas Baumann, Felix Krause, Michael Neumayr, Nick Stracke, Vincent Tao Hu, Björn Ommer

We demonstrate that these directions can be used to augment the prompt text input with fine-grained control over attributes of specific subjects in a compositional manner (control over multiple attributes of a single subject) without having to adapt the diffusion model.


ZigMa: A DiT-style Zigzag Mamba Diffusion Model

1 code implementation20 Mar 2024 Vincent Tao Hu, Stefan Andreas Baumann, Ming Gui, Olga Grebenkova, Pingchuan Ma, Johannes Fischer, Björn Ommer

The diffusion model has long been plagued by scalability and quadratic complexity issues, especially within transformer-based structures.

Training Class-Imbalanced Diffusion Model Via Overlap Optimization

no code implementations16 Feb 2024 Divin Yan, Lu Qi, Vincent Tao Hu, Ming-Hsuan Yang, Meng Tang

To address the observed appearance overlap between synthesized images of rare classes and tail classes, we propose a method based on contrastive learning to minimize the overlap between distributions of synthetic images for different classes.

Contrastive Learning Image Generation

Latent Space Editing in Transformer-Based Flow Matching

no code implementations17 Dec 2023 Vincent Tao Hu, David W Zhang, Pascal Mettes, Meng Tang, Deli Zhao, Cees G. M. Snoek

Flow Matching is an emerging generative modeling technique that offers the advantage of simple and efficient training.

Motion Flow Matching for Human Motion Synthesis and Editing

no code implementations14 Dec 2023 Vincent Tao Hu, Wenzhe Yin, Pingchuan Ma, Yunlu Chen, Basura Fernando, Yuki M Asano, Efstratios Gavves, Pascal Mettes, Bjorn Ommer, Cees G. M. Snoek

In this paper, we propose \emph{Motion Flow Matching}, a novel generative model designed for human motion generation featuring efficient sampling and effectiveness in motion editing applications.

Motion Interpolation motion prediction +1

Guided Diffusion from Self-Supervised Diffusion Features

no code implementations14 Dec 2023 Vincent Tao Hu, Yunlu Chen, Mathilde Caron, Yuki M. Asano, Cees G. M. Snoek, Bjorn Ommer

However, recent studies have revealed that the feature representation derived from diffusion model itself is discriminative for numerous downstream tasks as well, which prompts us to propose a framework to extract guidance from, and specifically for, diffusion models.

Self-Supervised Learning

ScribbleGen: Generative Data Augmentation Improves Scribble-supervised Semantic Segmentation

no code implementations28 Nov 2023 Jacob Schnell, Jieke Wang, Lu Qi, Vincent Tao Hu, Meng Tang

We propose ScribbleGen, a generative data augmentation method that leverages a ControlNet diffusion model conditioned on semantic scribbles to produce high-quality training data.

Data Augmentation Image Classification +4

ToddlerDiffusion: Flash Interpretable Controllable Diffusion Model

no code implementations24 Nov 2023 Eslam Mohamed BAKR, Liangbing Zhao, Vincent Tao Hu, Matthieu Cord, Patrick Perez, Mohamed Elhoseiny

Diffusion-based generative models excel in perceptually impressive synthesis but face challenges in interpretability.

Denoising Image Generation

Self-Guided Diffusion Models

1 code implementation CVPR 2023 Vincent Tao Hu, David W Zhang, Yuki M. Asano, Gertjan J. Burghouts, Cees G. M. Snoek

Diffusion models have demonstrated remarkable progress in image generation quality, especially when guidance is used to control the generative process.

Image Generation

Self-supervised Video Representation Learning with Cross-Stream Prototypical Contrasting

1 code implementation18 Jun 2021 Martine Toering, Ioannis Gatopoulos, Maarten Stol, Vincent Tao Hu

Instance-level contrastive learning techniques, which rely on data augmentation and a contrastive loss function, have found great success in the domain of visual representation learning.

Action Recognition In Videos Contrastive Learning +10

Localizing the Common Action Among a Few Videos

1 code implementation ECCV 2020 Pengwan Yang, Vincent Tao Hu, Pascal Mettes, Cees G. M. Snoek

The start and end of an action in a long untrimmed video is determined based on just a hand-full of trimmed video examples containing the same action, without knowing their common class label.

Action Localization

Cannot find the paper you are looking for? You can Submit a new open access paper.