paper-with-me

홈 › Papers

Probabilistic and Semantic Descriptions of Image Manifolds and Their Applications

2023-07-06 · Peter Tu, Zhaoyuan Yang, Richard Hartley, Zhiwei Xu, Jing Zhang, Yiwei Fu, Dylan Campbell, Jaskirat Singh, Tianyu Wang

This paper begins with a description of methods for estimating image probability density functions that reflects the observation that such data is usually constrained to lie in restricted regions of the high-dimensional image space-not every pattern of pixels is an image. It is common to say that images lie on a lower-dimensional manifold in the high-dimensional space. However, it is not the case that all points on the manifold have an equal probability of being images. Images are unevenly distributed on the manifold, and our task is to devise ways to model this distribution as a probability distribution. We therefore consider popular generative models. For our purposes, generative/probabilistic models should have the properties of 1) sample generation: the possibility to sample from this distribution with the modelled density function, and 2) probability computation: given a previously unseen sample from the dataset of interest, one should be able to compute its probability, at least up to a normalising constant. To this end, we investigate the use of methods such as normalising flow and diffusion models. We then show how semantic interpretations are used to describe points on the manifold. To achieve this, we consider an emergent language framework that uses variational encoders for a disentangled representation of points that reside on a given manifold. Trajectories between points on a manifold can then be described as evolving semantic descriptions. We also show that such probabilistic descriptions (bounded) can be used to improve semantic consistency by constructing defences against adversarial attacks. We evaluate our methods with improved semantic robustness and OoD detection capability, explainable and editable semantic interpolation, and improved classification accuracy under patch attacks. We also discuss the limitation in diffusion models.

📄 PDF Abstract BibTeX arXiv:2307.02881

Code (0)

등록된 구현이 없습니다.

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

A Geometric Unification of Generative AI with Manifold-Probabilistic Projection Models

2025-10-01 · Leah Bar, Liron Mor Yosef, Shai Zucker, Neta Shoham 외 arxiv

Most models of generative AI for images assume that images are inherently low-dimensional objects embedded within a high-dimensional space. Additionally, it is often implicitly assumed that thematic image datasets form s…

Image RestorationImage Denoising

Normalizing Flows on the Product Space of SO(3) Manifolds for Probabilistic Human Pose Modeling

2024-04-08 · CVPR 2024 1 · Olaf Dünkel, Tim Salzmann, Florian Pfaff

Normalizing flows have proven their efficacy for density estimation in Euclidean space, but their application to rotational representations, crucial in various domains such as robotics or human pose modeling, remains und…

Density Estimation

ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models

2026-01-23 · Chenxi Ruan, Yihan Hou, Yu Xiao, Guosheng Hu 외 arxiv

Text-to-image (T2I) models have advanced considerably in generating high-quality images from textual descriptions. However, their ability to associate colors with concepts remains largely constrained to explicit color na…

Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics

2023-01-16 · NeurIPS 2023 11 · Mu Niu, Zhenwen Dai, Pokman Cheung, Yizhu Wang

This article presents a novel approach to construct Intrinsic Gaussian Processes for regression on unknown manifolds with probabilistic metrics (GPUM) in point clouds. In many real world applications, one often encounter…

Gaussian ProcessesUncertainty Quantification

Probabilistic Lexical Manifold Construction in Large Language Models via Hierarchical Vector Field Interpolation

2025-02-14 · Clive Pendleton, Ewan Harrington, Giles Fairbrother, Jasper Arkwright 외

Hierarchical vector field interpolation introduces a structured probabilistic framework for lexical representation, ensuring that word embeddings transition smoothly across a continuous manifold rather than being constra…

Computational EfficiencyRepresentation LearningWord Embeddings