Editing a classifier by rewriting its prediction rules

Last update: Dec 27, 2022

Related tags

Overview

This repository contains the code and data for our paper:

Editing a classifier by rewriting its prediction rules
Shibani Santurkar*, Dimitris Tsipras*, Mahi Elango, David Bau, Antonio Torralba, Aleksander Madry
Paper: https://arxiv.org/abs/2112.01008

    @InProceedings{santurkar2021editing,
        title={Editing a classifier by rewriting its prediction rules},
        author={Shibani Santurkar and Dimitris Tsipras and Mahalaxmi Elango and David Bau and Antonio Torralba and Aleksander Madry},
        year={2021},
        booktitle={Neural Information Processing Systems (NeurIPS)}
    }

Getting started

You can start by cloning our repository and following the steps below. Parts of this codebase have been derived from the GAN rewriting repository of Bau et al.

Install the dependencies for our code using Conda. You may need to adjust the environment YAML file depending on your setup.
```
conda env create -f environment.yaml
```
Download model checkpoints and extract them in the current directory.

To instantiate CLIP

git submodule init
git submodule update

Replace IMAGENET_PATH in helpers/classifier_helpers.py with the path to the ImageNet dataset.
(If using synthetic examples) Download files segmentations.tar.gz and styles.tar.gz and extract them under ./data/synthetic.
(If using synthetic examples) Run

     python stylize.py --style_name [STYLE_FILE_NAME]

with the desired style file from ./data/synthetic/styles. You could also use a custom style file if desired.

That's it! Now you can explore our editing methodology in various settings: vehicles-on-snow, typographic attacks and synthetic test cases.

Maintainers

Simple embedding based text classifier inspired by fastText, implemented in tensorflow

FastText in Tensorflow This project is based on the ideas in Facebook's FastText but implemented in Tensorflow. However, it is not an exact replica of

306 Dec 2, 2022

CondNet: Conditional Classifier for Scene Segmentation

CondNet: Conditional Classifier for Scene Segmentation Introduction The fully convolutional network (FCN) has achieved tremendous success in dense vis

31 Jul 22, 2022

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples This project is for the paper "Training Confidence-Calibrated Clas

168 Nov 29, 2022

Open-Set Recognition: A Good Closed-Set Classifier is All You Need

Open-Set Recognition: A Good Closed-Set Classifier is All You Need Code for our paper: "Open-Set Recognition: A Good Closed-Set Classifier is All You

194 Jan 3, 2023

The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

Published by SpaceML • About SpaceML • Quick Colab Example Self-Supervised Learner The Self-Supervised Learner can be used to train a classifier with

92 Nov 30, 2022

This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization This codebase is the official implementation of Test-Time Classifier A

47 Dec 28, 2022

A method that utilized Generative Adversarial Network (GAN) to interpret the black-box deep image classifier models by PyTorch.

3 Dec 29, 2022

Training Cifar-10 Classifier Using VGG16

opevcvdl-hw3 This project uses pytorch and Qt to achieve the requirements. Version Python 3.6 opencv-contrib-python 3.4.2.17 Matplotlib 3.1.1 pyqt5 5.

3 Aug 17, 2022

Yoga - Yoga asana classifier for python

Yoga Asana Classifier Description Hi welcome to my new deep learning project "Yo

35 Dec 12, 2022

Editing a classifier by rewriting its prediction rules

Related tags

Overview

Getting started

Maintainers

You might also like...

Simple embedding based text classifier inspired by fastText, implemented in tensorflow

CondNet: Conditional Classifier for Scene Segmentation

Training Confidence-Calibrated Classifier for Detecting Out-of-Distribution Samples / ICLR 2018

Open-Set Recognition: A Good Closed-Set Classifier is All You Need

The Self-Supervised Learner can be used to train a classifier with fewer labeled examples needed using self-supervised learning.

This codebase is the official implementation of Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (NeurIPS2021, Spotlight)

A method that utilized Generative Adversarial Network (GAN) to interpret the black-box deep image classifier models by PyTorch.

Training Cifar-10 Classifier Using VGG16

Yoga - Yoga asana classifier for python

Releases(v1)

v1(Dec 2, 2021)

Owner

Madry Lab

Multispectral Object Detection with Yolov5

Pyramid Pooling Transformer for Scene Understanding

An official source code for "Augmentation-Free Self-Supervised Learning on Graphs"

WHENet: Real-time Fine-Grained Estimation for Wide Range Head Pose

Codes accompanying the paper "Believe What You See: Implicit Constraint Approach for Offline Multi-Agent Reinforcement Learning" (NeurIPS 2021 Spotlight

Compositional Sketch Search

PyTorch EO aims to make Deep Learning for Earth Observation data easy and accessible to real-world cases and research alike.

Cross View SLAM

Pytorch and Keras Implementations of Hyperspectral Image Classification -- Traditional to Deep Models: A Survey for Future Prospects.

Re-implementation of the vector capsule with dynamic routing

VOGUE: Try-On by StyleGAN Interpolation Optimization

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

Get started with Machine Learning with Python - An introduction with Python programming examples

Official MegEngine implementation of CREStereo(CVPR 2022 Oral).

Repository for MuSiQue: Multi-hop Questions via Single-hop Question Composition

Task-related Saliency Network For Few-shot learning

Supervised domain-agnostic prediction framework for probabilistic modelling

CLOOB: Modern Hopfield Networks with InfoLOOB Outperform CLIP

A nutritional label for food for thought.

QHack—the quantum machine learning hackathon