rgeirhos

google-research

Google Research

tuning_playbook

A playbook for systematically maximizing the performance of deep learning models.

zotero

Zotero is a free, easy-to-use tool to help you collect, organize, annotate, cite, and share your research sources.

dinov2

PyTorch code and models for the DINOv2 self-supervised learning method.

datasets

TFDS is a collection of datasets ready to use with TensorFlow, Jax, ...

visual_anagrams

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

ImageNet21K

Official Pytorch Implementation of: "ImageNet-21K Pretraining for the Masses"(NeurIPS, 2021) paper

lucent

Lucid library adapted for PyTorch

self-refine

LLMs can generate feedback on their work, use it to improve the output, and repeat this process iteratively.

vision

A framework for evaluating models on their alignment to brain and behavioral measurements (50+ benchmarks)

deep_feature_reweighting

dataset-pruning-metrics

Metrics for "Beyond neural scaling laws: beating power law scaling via data pruning " (NeurIPS 2022 Outstanding Paper Award)

icml-2022

Crowdsourcing metrics and test datasets beyond ImageNet (ICML 2022 workshop)

fooling-feature-visualizations

Code for "Don't trust your eyes: on the (un)reliability of feature visualizations"

spurious_imagenet

Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet

CCC

Code for Continuously Changing Corruptions (CCC) benchmark + evaluation

interpretability-theory

NINCO

Code and data for the paper "In or Out? Fixing ImageNet Out-of-Distribution Detection Evaluation"

cblearn

Comparison-based Machine Learning in Python

ObjectPose

humanlike-vits

ViT models pretrained with up to ~5k hours of human-like video data

trapped-in-texture-bias

Official code release for the paper Trapped in texture bias? A large scale comparison of deep instance segmentation, accepted at ECCV 2022

CLIP-imagenet-evaluation

Run CLIP inference on the ImageNet dataset and use these inferences as labels to train other models and again evaluate the trained model on Imagenet validation dataset using original labels or CLIP labels

awesome-representational-alignment

A curated list of representational alignment papers, projects, and presentations

robustness-development

trivial-or-impossible

Code for "Trivial or impossible—dichotomous data difficulty masks model differences (on ImageNet and beyond)" (ICLR 2022)

linux-sort-iCloud-photos

Script to sort photos from iCloud on Linux by date

do_users_benefit_from_interpretable_vision

diffusion-noise-cls-pytorch

This is an unofficial implementation of the diffusion-style noise frontend in "Intriguing properties of generative classifiers" by Priyank Jaini, Kevin Clark, Robert Geirhos to improve the shape-bias of vision models.

neural_harmonizer

Oficial implementation of the paper Performance-optimized DNNs are evolving into worse models of inferotemporal visual cortex