IDIM - ID as a Model-Free Measure of Class Imbalance

This repository contains the official implementation of:
“Intrinsic Dimensionality as a Model-Free Measure of Class Imbalance”
Çağrı Eser, Zeynep Sonat Baltacı, Emre Akbaş, and Sinan Kalkan.

Paper (arXiv): https://arxiv.org/abs/2511.10475

Table of Contents

• Setup
• Repository Structure
• Usage
  • Estimating ID
  • Using ID with Long-Tailed Methods
• Results
• Pretrained Models
• Citation
• Contact

Setup

We recommend using Python 3.8+ and a virtual environment (e.g. conda). Dependencies (for ID estimation) to be installed (via pip, conda, etc.) include:

• torch >= 1.12.0 and any appropriate version of torchvision
• numpy
• scikit-dimension
• tqdm

For dependencies of individual integrations, please consult the relative README file of the respective method under methods/.

Repository Structure

.
├── docs/
├── methods/
│   ├── Bag-of-Tricks/
│   ├── BCL/
│   ├── DRO-LT/
│   ├── GLMC/
│   ├── logit_adjustment/
│   └── SURE/
├── utils/
│   └── id-estimation/
│       ├── id_cifar.py
│       ├── id_imagenet.py
│       ├── id_places.py
│       └── README.md
├── LICENSE
└── README.md

Usage

ID Estimation

We provide scripts to estimate ID on CIFAR-LT, PlacesLT and ImageNet-LT datasets in the utils/id-estimation directory.

Using ID with Long-Tailed Methods

This directory contains code for using our ID-based method with multiple integrations:

• Bag of Tricks (Zhang et al., 2021)
• Logit Adjustment (Menon et al., 2021)
• DRO-LT (Samuel and Chechik, 2021)
• BCL (Zhu et al., 2022)
• GLMC (Du et al., 2023)
• SURE (Li et al., 2024)

Each method has a dedicated directory under methods/ with its own instructions and an ID.md file describing how to plug in our ID-based measure.

Results

Pretrained Models

We release a subset of the models used in the paper.

Dataset	Method	Imbalance Ratio	Top-1 Accuracy	Checkpoints and Logs
CIFAR-10-LT	GLMC + ID	100	87.9	link
		50	90.5	link
CIFAR-100-LT	GLMC + ID	100	58.0	link
		50	62.8	link
CIFAR-10-LT	SURE + RW + ID	100	87.0	link
		50	90.4	link
CIFAR-100-LT	SURE + RW + ID	100	57.7	link
		50	62.7	link

Dataset	Method	Backbone	Top-1 Accuracy	Checkpoints and Logs
Places-LT	BoT + ID	ResNet-152	43.4	link
ImageNet-LT	BoT + ID	ResNet-10	42.9	link
ImageNet-LT	GLMC + ID	ResNeXt-50	56.3	link
ImageNet-LT	BCL + ID	ResNet-50 (90EP)	56.5	link
ImageNet-LT	BCL + ID	ResNeXt-50 (90EP)	57.9	link
ImageNet-LT	BCL + ID	ResNeXt-50 (180EP)	58.2	link

Citation

If you would like to cite this work, please use:

@article{eser2025intrinsic,
  title={Intrinsic Dimensionality as a Model-Free Measure of Class Imbalance},
  author={Cagri Eser and Zeynep Sonat Baltaci and Emre Akbas and Sinan Kalkan},
  journal={arXiv preprint arXiv:2511.10475},
  year={2025}
}

Contact

For questions and suggestions, please contact:

• Cagri Eser - cagri.eser@metu.edu.tr