arXiv Machine Learning
What Does Fr\'echet Distance Measure? A Directional Decomposition
Read the original on arXiv Machine Learning →The Flow has not summarised this story yet — read it at arXiv Machine Learning.
Related stories
arXiv Computer Vision
Sep 10
UOT-Gap: A Variational Principle for the Modality Gap in Vision-Language Models via Unbalanced Optimal Transport
arXiv:2609.10224v1 Announce Type: new Abstract: Vision-language models such as CLIP embed images and text in a shared space, where modality-specific distributions often remain separated. Existing acc...
arXiv Machine Learning
Aug 26
What FID Hides: Detecting, Ranking, and Diagnosing Deviations in Generative Evaluation
arXiv:2608.24881v1 Announce Type: cross Abstract: Generative models are commonly ranked by Fr\'echet Inception Distance (FID) and Kernel Inception Distance (KID), yet FID's first-two-moment summary c...
arXiv AI
Oct 9
APEX: Assumption-free Projection-based Embedding eXamination Metric for Image Quality Assessment
APEX is a new image quality assessment framework that eliminates assumptions by using the Sliced Wasserstein Distance as a similarity measure. It is embedding‑agnostic, scalable to high‑dimensional spaces, and employs open‑vocabulary models CLIP and DINOv2 for feature extraction. Benchmarks show that APEX is more robust to visual degradations and remains stable across different datasets, including out‑of‑domain ones.
arXiv Computer Vision
Sep 30
Evaluating Generative Models via One-Dimensional Code Distributions
arXiv:2603.08064v3 Announce Type: replace Abstract: Most evaluations of generative models rely on feature-distribution metrics such as FID, which operate on continuous recognition features that are e...
arXiv AI
Oct 15
APEX: Assumption-free Projection-based Embedding eXamination Metric for Generative Distribution Evaluation
arXiv:2605.07786v4 Announce Type: replace-cross Abstract: As generative models achieve unprecedented visual quality, the gold standard for image evaluation remains traditional feature-distribution me...
arXiv Computer Vision
Sep 23
FoMo: Forking Moment in Generative Trajectory as a Perceptual Distance
arXiv:2609.25716v1 Announce Type: new Abstract: Reference-based image quality assessment (IQA) metrics aim to reflect how humans perceive the perceptual distance between a pair of images. To learn ho...