metadata
license: cc-by-nc-sa-4.0
library_name: pytorch
pipeline_tag: image-feature-extraction
datasets:
- fdsml/FineFractalDB
tags:
- fdsml
- formula-driven-supervised-learning
- metric-learning
- fractal
- synthetic-data
- pre-training
- resnet
- arxiv:2610.39423
FDSML ResNet-50 — diff strategy
ResNet-50 pre-trained on FineFractalDB with FDSML (Formula-Driven Supervised Metric Learning) using the Parameter-Aware Triplet Loss and the diff triplet selection strategy. No natural images are used during pre-training. The main ResNet-50 results in the paper use the same strategy.
- Paper: https://arxiv.org/abs/2610.39423
- Project page: https://shineiarakawa.github.io/fdsml/
- Code: https://github.com/ShineiArakawa/fdsml
- Dataset: https://huggingface.co/datasets/fdsml/FineFractalDB
Model details
| Item | Value |
|---|---|
| Architecture | ResNet-50 (25.6M parameters) |
| Pre-training data | FineFractalDB (1,000 IFS classes × 1,000 images, synthetic) |
| Objective | Parameter-Aware Triplet Loss |
| Triplet strategy | diff (diff_class): selects all pairs from different classes |
| Projection dim | 512 |
| Training images seen | 134,217k (134.22 epochs) |
| Checkpoint | checkpoint-134217kimg-134.22ep_fdsml_resnet50_diff.pt |
| Name in the official code | resnet50_fdsml_diff_pretrained |
Usage
The checkpoint is a plain PyTorch file and is loaded with the official code.
import torch
from huggingface_hub import hf_hub_download
path = hf_hub_download("fdsml/fdsml-finefractaldb-resnet50-diff", "checkpoint-134217kimg-134.22ep_fdsml_resnet50_diff.pt")
ckpt = torch.load(path, map_location="cpu")
To fine-tune on a downstream task, pass the checkpoint to finetune.py:
torchrun --standalone --nproc_per_node=4 finetune.py \
--net=resnet50 \
--ckpt=/path/to/checkpoint-134217kimg-134.22ep_fdsml_resnet50_diff.pt \
--dset=/path/to/imagenet
See the README for the full list of options and the exact configurations used in the paper.
Citation
@inproceedings{Otake2027fdsml,
title = {FDSML: Formula-Driven Supervised Metric Learning with Parameter-Aware Triplet Loss},
author = {Hina Otake and Shinei Arakawa and Keitaro Tanaka and Yoshihiro Fukuhara and Hirokatsu Kataoka and Shigeo Morishima},
booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)},
year = {2027},
}
License
Released under CC BY-NC-SA 4.0. Non-commercial use only.