View selection for 3d captioning via diffusion ranking

T Luo, J Johnson, H Lee - European Conference on Computer Vision, 2024 - Springer
Scalable annotation approaches are crucial for constructing extensive 3D-text datasets,
facilitating a broader range of applications. However, existing methods sometimes lead to …

Representation alignment for generation: Training diffusion transformers is easier than you think

S Yu, S Kwak, H Jang, J Jeong, J Huang, J Shin… - arxiv preprint arxiv …, 2024 - arxiv.org
Recent studies have shown that the denoising process in (generative) diffusion models can
induce meaningful (discriminative) representations inside the model, though the quality of …

Deconstructing denoising diffusion models for self-supervised learning

X Chen, Z Liu, S **e, K He - arxiv preprint arxiv:2401.14404, 2024 - arxiv.org
In this study, we examine the representation learning abilities of Denoising Diffusion Models
(DDM) that were originally purposed for image generation. Our philosophy is to deconstruct …

Diffusion-ss3d: Diffusion model for semi-supervised 3d object detection

CJ Ho, CH Tai, YY Lin, MH Yang… - Advances in Neural …, 2023 - proceedings.neurips.cc
Semi-supervised object detection is crucial for 3D scene understanding, efficiently
addressing the limitation of acquiring large-scale 3D bounding box annotations. Existing …

Diffusion models and representation learning: A survey

M Fuest, P Ma, M Gui, JS Fischer, VT Hu… - arxiv preprint arxiv …, 2024 - arxiv.org
Diffusion Models are popular generative modeling methods in various vision tasks, attracting
significant attention. They can be considered a unique instance of self-supervised learning …

Ecg synthesis via diffusion-based state space augmented transformer

MH Zama, F Schwenker - Sensors, 2023 - mdpi.com
Cardiovascular diseases (CVDs) are a major global health concern, causing significant
morbidity and mortality. AI's integration with healthcare offers promising solutions, with data …

Image understanding makes for a good tokenizer for image generation

L Wang, Y Zhao, Z Zhang, J Feng, S Liu… - arxiv preprint arxiv …, 2024 - arxiv.org
Modern image generation (IG) models have been shown to capture rich semantics valuable
for image understanding (IU) tasks. However, the potential of IU models to improve IG …

Diff3DETR: Agent-Based Diffusion Model for Semi-supervised 3D Object Detection

J Deng, J Lu, T Zhang - European Conference on Computer Vision, 2024 - Springer
Abstract 3D object detection is essential for understanding 3D scenes. Contemporary
techniques often require extensive annotated training data, yet obtaining point-wise …

Balancing Act: Distribution-Guided Debiasing in Diffusion Models

R Parihar, A Bhat, A Basu, S Mallick… - Proceedings of the …, 2024 - openaccess.thecvf.com
Abstract Diffusion Models (DMs) have emerged as powerful generative models with
unprecedented image generation capability. These models are widely used for data …

ToDA: Target-oriented Diffusion Attacker against Recommendation System

X Liu, Z Tao, T Jiang, H Chang, Y Ma, Y Wei… - arxiv preprint arxiv …, 2024 - arxiv.org
Recommendation systems (RS) have become indispensable tools for web services to
address information overload, thus enhancing user experiences and bolstering platforms' …