FDSML：用参数感知三元组损失从公式生成参数中学习度量

View PDF HTML (experimental)

Abstract:Formula-Driven Supervised Learning (FDSL) enables vision pre-training without real images, but existing methods cast pre-training as classification on discretized labels, discarding continuity in the generative process. We propose Formula-Driven Supervised Metric Learning (FDSML), which derives relational supervision from image-generation parameters beyond discrete class labels. FDSML combines FineFractalDB, our refined fractal dataset with higher intra-class variation and more stable structures, with a Parameter-Aware Triplet (PA-Triplet) Loss that assigns positives and negatives according to distances in the underlying Iterated Function System parameter space. This objective trains embeddings to respect parameter-derived relative similarity orderings. Experiments show that FDSML improves transferability to image retrieval while remaining competitive on downstream classification and improving robustness under several corruption settings. On ResNet-50, Recall@1 improves from 65.6% to 74.0% on Stanford Online Products and from 56.2% to 78.4% on Stanford Cars over FDSL pre-training. These results suggest that parameter-derived relational supervision provides a stronger synthetic pre-training signal than label-based classification for transfer beyond recognition.

Comments:	Accepted to WACV 2027. 24 pages (11 main + 13 supplementary). Project page: this https URL
Subjects:	Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Neural and Evolutionary Computing (cs.NE)
Cite as:	arXiv:2610.39423 [cs.CV]
	(or arXiv:2610.39423v1 [cs.CV] for this version)
	https://doi.org/10.48550/arXiv.2610.39423 arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Shinei Arakawa [view email]
[v1] Thu, 29 Oct 2026 06:02:45 UTC (28,841 KB)