跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 24 天前AI 評分37

FDSML:公式驅動監督式度量學習與參數感知三元組損失

FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss

AI 導讀

FDSML提出以生成參數提供關係監督的度量學習方法,結合 FineFractalDB 和 PA-Triplet Loss,利用迭代函數系統參數空間中的距離設定正、負樣本,訓練影像嵌入向量。

正文

Published on Oct 29

Authors:

,

,

,

,

Abstract

Formula-driven supervised metric learning uses continuous generative parameters to train embeddings with parameter-aware triplet loss, improving synthetic pre-training for image retrieval and robustness.

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.

View arXiv page View PDF Project page GitHub 0 Add to collection

Community

Paper author

Paper submitter

8 minutes ago

FDSML pre-trains vision models without real images, using the generating formula itself as supervision: fractals with more similar parameters should lie closer in the embedding space. We turn this parameter-space ordering into triplets, so the model learns how images relate to each other.

Get this paper in your agent:

hf papers read 2610.39423

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 12

FDSML/fdsml-finefractaldb-resnet50-all

Image Feature Extraction •

Updated about 8 hours ago

FDSML/fdsml-finefractaldb-resnet50-diff

Image Feature Extraction •

Updated about 8 hours ago

FDSML/fdsml-finefractaldb-resnet50-each

Image Feature Extraction •

Updated about 8 hours ago

FDSML/fdsml-finefractaldb-resnet50-same

Image Feature Extraction •

Updated about 8 hours ago

Browse 12 models citing this paper

Datasets citing this paper 1

FDSML/FineFractalDB

Viewer •

Updated about 8 hours ago

•

1M

•

68

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.39423 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co