paper-with-me

홈 › Papers

Rethinking cluster-conditioned diffusion models for label-free image synthesis

2024-03-01 · Nikolas Adaloglou, Tim Kaiser, Felix Michels, Markus Kollmann

Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. Here, we conduct a comprehensive experimental study on image-level conditioning for diffusion models using cluster assignments. We investigate how individual clustering determinants, such as the number of clusters and the clustering method, impact image synthesis across three different datasets. Given the optimal number of clusters with respect to image synthesis, we show that cluster-conditioning can achieve state-of-the-art performance, with an FID of 1.67 for CIFAR10 and 2.17 for CIFAR100, along with a strong increase in training sample efficiency. We further propose a novel empirical method to estimate an upper bound for the optimal number of clusters. Unlike existing approaches, we find no significant association between clustering performance and the corresponding cluster-conditional FID scores. The code is available at https://github.com/HHU-MMBS/cedm-official-wavc2025.

📄 PDF Abstract BibTeX arXiv:2403.00570

Code (1)

hhu-mmbs/cedm-official-wavc2025 공식 구현 pytorch

Tasks

ClusteringConditional Image GenerationImage ClusteringImage Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Rethinking Independent Cross-Entropy Loss For Graph-Structured Data

2024-05-24 · Rui Miao, Kaixiong Zhou, Yili Wang, Ninghao Liu 외

Graph neural networks (GNNs) have exhibited prominent performance in learning graph-structured data. Considering node classification task, based on the i.i.d assumption among node labels, the traditional supervised learn…

Adversarial AttackNode Classification

Label-free Motion-Conditioned Diffusion Model for Cardiac Ultrasound Synthesis

2025-12-10 · Zhe Li, Hadrien Reynaud, Johanna P Müller, Bernhard Kainz arxiv

Ultrasound echocardiography is essential for the non-invasive, real-time assessment of cardiac function, but the scarcity of labelled data, driven by privacy restrictions and the complexity of expert annotation, remains …

Video Generation

Local Graph Clustering with Noisy Labels

2023-10-12 · Artur Back de Luca, Kimon Fountoulakis, Shenghao Yang

The growing interest in machine learning problems over graphs with additional node information such as texts, images, or labels has popularized methods that require the costly operation of processing the entire graph. Ye…

ClusteringGraph Clustering

Why Are Conditional Generative Models Better Than Unconditional Ones?

2022-12-01 · Fan Bao, Chongxuan Li, Jiacheng Sun, Jun Zhu

Extensive empirical evidence demonstrates that conditional generative models are easier to train and perform better than unconditional ones by exploiting the labels of data. So do score-based diffusion models. In this pa…

Goal-Conditioned Imitation Learning using Score-based Diffusion Policies

2023-04-05 · Moritz Reuss, Maximilian Li, Xiaogang Jia, Rudolf Lioutikov

We propose a new policy representation based on score-based diffusion models (SDMs). We apply our new policy representation in the domain of Goal-Conditioned Imitation Learning (GCIL) to learn general-purpose goal-specif…

DenoisingImitation LearningRobot Manipulation