Related papers: GeoDM: Geometry-aware Distribution Matching for Da…

Homology-based invariants can be used to characterize the geometry of datasets and thereby gain some understanding of the processes generating those datasets. In this work we investigate how the geometry of a dataset changes when it is…

In image set classification, a considerable progress has been made by representing original image sets on Grassmann manifolds. In order to extend the advantages of the Euclidean based dimensionality reduction methods to the Grassmann…

Deep learning technology has developed unprecedentedly in the last decade and has become the primary choice in many application domains. This progress is mainly attributed to a systematic collaboration in which rapidly growing computing…

The performance of a lifelong learning (L3) model degrades when it is trained on a series of tasks, as the geometrical formation of the embedding space changes while learning novel concepts sequentially. The majority of existing L3…

Recent advances in fast sampling methods for diffusion models have demonstrated significant potential to accelerate generation on image modalities. We apply these methods to 3-dimensional molecular conformations by building on the recently…

Deep Metric Learning (DML) methods have been proven relevant for visual similarity learning. However, they sometimes lack generalization properties because they are trained often using an inappropriate sample selection strategy or due to…

Dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space…

Dataset Distillation (DD) aims to synthesize a small dataset capable of performing comparably to the original dataset. Despite the success of numerous DD methods, theoretical exploration of this area remains unaddressed. In this paper, we…

Deep metric learning aims to transform input data into an embedding space, where similar samples are close while dissimilar samples are far apart from each other. In practice, samples of new categories arrive incrementally, which requires…

The extensive amounts of data required for training deep neural networks pose significant challenges on storage and transmission fronts. Dataset distillation has emerged as a promising technique to condense the information of massive…

A generative modeling framework is proposed that combines diffusion models and manifold learning to efficiently sample data densities on manifolds. The approach utilizes Diffusion Maps to uncover possible low-dimensional underlying (latent)…

Dataset distillation has emerged as an effective strategy, significantly reducing training costs and facilitating more efficient model deployment. Recent advances have leveraged generative models to distill datasets by capturing the…

Dataset distillation is an emerging dataset reduction method, which condenses large-scale datasets while maintaining task accuracy. Current parameterization methods achieve enhanced performance under extremely high compression ratio by…

We introduce {\em vector diffusion maps} (VDM), a new mathematical framework for organizing and analyzing massive high dimensional data sets, images and shapes. VDM is a mathematical and algorithmic generalization of diffusion maps and…

Codistillation has been proposed as a mechanism to share knowledge among concurrently trained models by encouraging them to represent the same function through an auxiliary loss. This contrasts with the more commonly used fully-synchronous…

Dataset distillation enables efficient training by distilling the information of large-scale datasets into significantly smaller synthetic datasets. Diffusion based paradigms have emerged in recent years, offering novel perspectives for…

Graph distillation (GD) is an effective approach to extract useful information from large-scale network structures. However, existing methods, which operate in Euclidean space to generate condensed graphs, struggle to capture the inherent…

Diffusion models are distinguished by their exceptional generative performance, particularly in producing high-quality samples through iterative denoising. While current theory suggests that the number of denoising steps required for…

Step distillation has become a leading technique for accelerating diffusion models, among which Distribution Matching Distillation (DMD) and Consistency Distillation are two representative paradigms. While consistency methods enforce…

We propose kernel-gradient drifting, a one-step generative modeling framework that replaces the fixed Euclidean displacement direction in drifting models with directions induced by the kernel itself. Standard drifting is attractive because…