arXiv AI
APEX: Assumption-free Projection-based Embedding eXamination Metric for Generative Distribution Evaluation
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
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
Aug 31
Image Augmentation as Test Generation for Deep Learning-Based Image Retrieval Systems
The paper reviews 50 image augmentation and generation techniques, categorizing them into ten groups, and conducts a large‑scale empirical study to assess their effectiveness as test generators for embedding‑based image retrieval systems. Using Amazon Titan and OpenCLIP embeddings, the authors evaluate the techniques across four dimensions—embedding‑space similarity, embedding uncertainty, semantic realism, and retrieval failure rate—on CIFAR‑10, ImageNet‑1K, and an industrial dataset. Results show that weather simulation and SaSPA yield the highest uncertainty and failure rates while maintaining realistic visuals, whereas GAN‑based methods produce low realism due to synthetic artifacts.
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 Machine Learning
Aug 6
Multimodal Alignment Through Joint Kernel Entropic Gromov--Wasserstein Optimal Transport
arXiv:2608. 04234v1 Announce Type: cross Abstract: We study the problem of aligning data from multiple modalities into a shared representation space, focusing on settings where strong pretrained unimodal encoders are available but cross-modal paired data are scarce.
arXiv Machine Learning
Oct 7
What Does Fr\'echet Distance Measure? A Directional Decomposition
arXiv:2610.05518v1 Announce Type: cross Abstract: The Fr\'echet distance is a de facto standard for evaluating generative models across domains, appearing as FID for images and FVD for videos. It sum...
arXiv Computer Vision
Oct 16
Auditing Metrics for Synthetic Data Utility: A Cross-Domain Study of Appearance and Geometry
The paper introduces SADGE, a quantitative similarity metric that predicts how well synthetic image datasets will perform on real-world computer vision tasks without requiring downstream model training. SADGE combines appearance and geometric similarity measures through a constrained bilinear interaction, outperforming appearance-only and geometry-only baselines across 79,000 image pairs in five synthetic-to-real benchmark families. The study demonstrates that the non‑linear interplay between appearance and geometry, rather than either alone, best predicts downstream performance in tasks such as object detection, semantic segmentation, and pose estimation.