Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight

Last update: Dec 10, 2022

Related tags

Overview

`dimensions`

Estimating the instrinsic dimensionality of image datasets

Code for: The Intrinsic Dimensionaity of Images and Its Impact On Learning - Phillip Pope and Chen Zhu, Ahmed Abdelkader, Micah Goldblum, Tom Goldstein (ICLR 2021, spotlight)

https://openreview.net/forum?id=XJk19XzGq2J

Environment

This code was developed in the following environment

conda create dimensions python=3.6 jupyter matplotlib scikit-learn pytorch==1.5.0 torchvision cudatoolkit=10.2 -c pytorch

To generate new data of controlled dimensionality with GANs, you must install:

pip install pytorch-pretrained-biggan

To use the shortest-path method (Granata and Carnevale 2016) you must also compile the fast graph shortest path code gsp (written by Jake VdP + Sci-Kit Learn)

cd estimators/gsp
python setup.py install

Generate data of controlled dimensionality

python generate_data/gen_images.py \
  --num_samples 1000 \
  --class_name basenji \
  --latent_dim 16 \
  --batch_size 100 \
  --save_dir samples/basenji_16

Estimate dimension of generated samples

To run the MLE (Levina and Bickel) estimator on the synthetic GAN data generated above:

python main.py \
    --estimator mle \
    --k1 25 \
    --single-k \
    --eval-every-k \
    --average-inverse \
    --dset  samples/basenji_16 \
    --max_num_samples 1000 \
    --save-path results/basenji_16.json

Use --estimators to try different estimators

Citation

If you find our paper or code useful, please cite our paper:

@inproceedings{DBLP:conf/iclr/PopeZAGG21,
  author    = {Phillip Pope and
               Chen Zhu and
               Ahmed Abdelkader and
               Micah Goldblum and
               Tom Goldstein},
  title     = {The Intrinsic Dimension of Images and Its Impact on Learning},
  booktitle = {9th International Conference on Learning Representations, {ICLR} 2021,
               Virtual Event, Austria, May 3-7, 2021},
  publisher = {OpenReview.net},
  year      = {2021},
  url       = {https://openreview.net/forum?id=XJk19XzGq2J},
  timestamp = {Wed, 23 Jun 2021 17:36:39 +0200},
  biburl    = {https://dblp.org/rec/conf/iclr/PopeZAGG21.bib},
  bibsource = {dblp computer science bibliography, https://dblp.org}
}

Acknowledgements

We gratefully acknowledge use of the following codebases when developing our dimensionality estimators:

We also thank Prof. Vishnu Boddeti for clarifying comments on the graph-distance estimator.

Disclaimer

This code released as is. We will do our best to address questions/bugs, but cannot guarantee support.

Code for "The Intrinsic Dimension of Images and Its Impact on Learning" - ICLR 2021 Spotlight

Related tags

Overview

`dimensions`

Environment

Generate data of controlled dimensionality

Estimate dimension of generated samples

Citation

Acknowledgements

Disclaimer

Owner

Phil Pope

The code release of paper Low-Light Image Enhancement with Normalizing Flow

Optimizes image files by converting them to webp while also updating all references.

DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs

Image Data Augmentation in Keras

SatelliteNeRF - PyTorch-based Neural Radiance Fields adapted to satellite domain

PyTorch Code for NeurIPS 2021 paper Anti-Backdoor Learning: Training Clean Models on Poisoned Data.

RIFE: Real-Time Intermediate Flow Estimation for Video Frame Interpolation

HSC4D: Human-centered 4D Scene Capture in Large-scale Indoor-outdoor Space Using Wearable IMUs and LiDAR. CVPR 2022

Python implementation of "Elliptic Fourier Features of a Closed Contour"

Style transfer, deep learning, feature transform

Python utility to generate filesystem content for Obsidian.

A python library for face detection and features extraction based on mediapipe library

The code for our paper submitted to RAL/IROS 2022: OverlapTransformer: An Efficient and Rotation-Invariant Transformer Network for LiDAR-Based Place Recognition.

PaddlePaddle GAN library, including lots of interesting applications like First-Order motion transfer, wav2lip, picture repair, image editing, photo2cartoon, image style transfer, and so on.

Contrastive Loss Gradient Attack (CLGA)

BabelCalib: A Universal Approach to Calibrating Central Cameras. In ICCV (2021)

Implementation of Neural Distance Embeddings for Biological Sequences (NeuroSEED) in PyTorch

Empirical Study of Transformers for Source Code & A Simple Approach for Handling Out-of-Vocabulary Identifiers in Deep Learning for Source Code

Madanalysis5 - A package for event file analysis and recasting of LHC results

OCTIS: Comparing Topic Models is Simple! A python package to optimize and evaluate topic models (accepted at EACL2021 demo track)