Saved in:
Bibliographic Details
Main Authors: Du, Ke, Peng, Yimin, Gao, Chao, Zhou, Fan, Xue, Siqiao
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.04394
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911251625410560
author Du, Ke
Peng, Yimin
Gao, Chao
Zhou, Fan
Xue, Siqiao
author_facet Du, Ke
Peng, Yimin
Gao, Chao
Zhou, Fan
Xue, Siqiao
contents DORAEMON is an open-source PyTorch library that unifies visual object modeling and representation learning across diverse scales. A single YAML-driven workflow covers classification, retrieval and metric learning; more than 1000 pretrained backbones are exposed through a timm-compatible interface, together with modular losses, augmentations and distributed-training utilities. Reproducible recipes match or exceed reference results on ImageNet-1K, MS-Celeb-1M and Stanford online products, while one-command export to ONNX or HuggingFace bridges research and deployment. By consolidating datasets, models, and training techniques into one platform, DORAEMON offers a scalable foundation for rapid experimentation in visual recognition and representation learning, enabling efficient transfer of research advances to real-world applications. The repository is available at https://github.com/wuji3/DORAEMON.
format Preprint
id arxiv_https___arxiv_org_abs_2511_04394
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scale
Du, Ke
Peng, Yimin
Gao, Chao
Zhou, Fan
Xue, Siqiao
Computer Vision and Pattern Recognition
DORAEMON is an open-source PyTorch library that unifies visual object modeling and representation learning across diverse scales. A single YAML-driven workflow covers classification, retrieval and metric learning; more than 1000 pretrained backbones are exposed through a timm-compatible interface, together with modular losses, augmentations and distributed-training utilities. Reproducible recipes match or exceed reference results on ImageNet-1K, MS-Celeb-1M and Stanford online products, while one-command export to ONNX or HuggingFace bridges research and deployment. By consolidating datasets, models, and training techniques into one platform, DORAEMON offers a scalable foundation for rapid experimentation in visual recognition and representation learning, enabling efficient transfer of research advances to real-world applications. The repository is available at https://github.com/wuji3/DORAEMON.
title DORAEMON: A Unified Library for Visual Object Modeling and Representation Learning at Scale
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.04394