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

• URL: http://arxiv.org/abs/2403.00570v2
• Date: Tue, 19 Nov 2024 11:00:38 GMT
• Title: Rethinking cluster-conditioned diffusion models for label-free image synthesis
• Authors: Nikolas Adaloglou, Tim Kaiser, Felix Michels, Markus Kollmann,
• Abstract summary: Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. We investigate how individual clustering determinants, such as the number of clusters and the clustering method, impact image synthesis.
• Score: 1.4624458429745086
• License:
• Abstract: 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.

Related papers

• Hierarchical Clustering for Conditional Diffusion in Image Generation [12.618079575423868]
  This paper introduces TreeDiffusion, a deep generative model that conditions Diffusion Models on hierarchical clusters to obtain high-quality, cluster-specific generations. The proposed pipeline consists of two steps: a VAE-based clustering model that learns the hierarchical structure of the data, and a conditional diffusion model that generates realistic images for each cluster.
  arXiv  Detail & Related papers  (2024-10-22T11:35:36Z)
• Image Clustering Algorithm Based on Self-Supervised Pretrained Models and Latent Feature Distribution Optimization [4.39139858370436]
  This paper introduces an image clustering algorithm based on self-supervised pretrained models and latent feature distribution optimization. Our approach outperforms the latest clustering algorithms and achieves state-of-the-art clustering results.
  arXiv  Detail & Related papers  (2024-08-04T04:08:21Z)
• A consensus-constrained parsimonious Gaussian mixture model for clustering hyperspectral images [0.0]
  Food engineers use hyperspectral images to classify the type and quality of a food sample. In order to train these methods, every pixel in each training image needs to be labelled. A consensus-constrained parsimonious Gaussian mixture model (ccPGMM) is proposed to label pixels in hyperspectral images.
  arXiv  Detail & Related papers  (2024-03-05T22:23:43Z)
• ClusterFormer: Clustering As A Universal Visual Learner [80.79669078819562]
  CLUSTERFORMER is a universal vision model based on the CLUSTERing paradigm with TransFORMER. It is capable of tackling heterogeneous vision tasks with varying levels of clustering granularity. For its efficacy, we hope our work can catalyze a paradigm shift in universal models in computer vision.
  arXiv  Detail & Related papers  (2023-09-22T22:12:30Z)
• C3: Cross-instance guided Contrastive Clustering [8.953252452851862]
  Clustering is the task of gathering similar data samples into clusters without using any predefined labels. We propose a novel contrastive clustering method, Cross-instance guided Contrastive Clustering (C3) Our proposed method can outperform state-of-the-art algorithms on benchmark computer vision datasets.
  arXiv  Detail & Related papers  (2022-11-14T06:28:07Z)
• On Mitigating Hard Clusters for Face Clustering [48.39472979642971]
  Face clustering is a promising way to scale up face recognition systems using large-scale unlabeled face images. We introduce two novel modules, Neighborhood-Diffusion-based Density (NDDe) and Transition-Probability-based Distance (TPDi) Our experiments on multiple benchmarks show that each module contributes to the final performance of our method.
  arXiv  Detail & Related papers  (2022-07-25T03:55:15Z)
• Multi-Facet Clustering Variational Autoencoders [9.150555507030083]
  High-dimensional data, such as images, typically feature multiple interesting characteristics one could cluster over. We introduce Multi-Facet Clustering Variational Autoencoders (MFCVAE) MFCVAE learns multiple clusterings simultaneously, and is trained fully unsupervised and end-to-end.
  arXiv  Detail & Related papers  (2021-06-09T17:36:38Z)
• Graph Contrastive Clustering [131.67881457114316]
  We propose a novel graph contrastive learning framework, which is then applied to the clustering task and we come up with the Graph Constrastive Clustering(GCC) method. Specifically, on the one hand, the graph Laplacian based contrastive loss is proposed to learn more discriminative and clustering-friendly features. On the other hand, a novel graph-based contrastive learning strategy is proposed to learn more compact clustering assignments.
  arXiv  Detail & Related papers  (2021-04-03T15:32:49Z)
• Scalable Hierarchical Agglomerative Clustering [65.66407726145619]
  Existing scalable hierarchical clustering methods sacrifice quality for speed. We present a scalable, agglomerative method for hierarchical clustering that does not sacrifice quality and scales to billions of data points.
  arXiv  Detail & Related papers  (2020-10-22T15:58:35Z)
• Contrastive Clustering [57.71729650297379]
  We propose Contrastive Clustering (CC) which explicitly performs the instance- and cluster-level contrastive learning. In particular, CC achieves an NMI of 0.705 (0.431) on the CIFAR-10 (CIFAR-100) dataset, which is an up to 19% (39%) performance improvement compared with the best baseline.
  arXiv  Detail & Related papers  (2020-09-21T08:54:40Z)
• LSD-C: Linearly Separable Deep Clusters [145.89790963544314]
  We present LSD-C, a novel method to identify clusters in an unlabeled dataset. Our method draws inspiration from recent semi-supervised learning practice and proposes to combine our clustering algorithm with self-supervised pretraining and strong data augmentation. We show that our approach significantly outperforms competitors on popular public image benchmarks including CIFAR 10/100, STL 10 and MNIST, as well as the document classification dataset Reuters 10K.
  arXiv  Detail & Related papers  (2020-06-17T17:58:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.