Improving Deep Network Debuggability via Sparse Decision Layers

Overview

Improving Deep Network Debuggability via Sparse Decision Layers

This repository contains the code for our paper:

Leveraging Sparse Linear Layers for Debuggable Deep Networks
Eric Wong*, Shibani Santurkar*, Aleksander Madry
Paper: http://arxiv.org/abs/2105.04857
Blog posts: Part1 and Part2

Pipeline overview

@article{wong2021leveraging,
  title={Leveraging Sparse Linear Layers for Debuggable Deep Networks},
  author={Wong, Eric and Santurkar, Shibani and M{\k{a}}dry, Aleksander},
  journal={arXiv preprint arXiv:2105.04857},
  year={2021}
}

Getting started

Our code relies on the MadryLab public robustness library, as well as the glm_saga library which will be automatically installed when you follow the instructions below. The glm_saga library contains a standalone implementation of our sparse GLM solver.

  1. Clone our repo: git clone https://github.com/microsoft/DebuggableDeepNetworks.git

  2. Setup the lucent submodule using: git submodule update --init --recursive

  3. We recommend using conda for dependencies:

    conda env create -f environment.yml
    conda activate debuggable
    

Training sparse decision layers

Contents:

  • main.py fits a sparse decision layer on top of the deep features of the specified pre-trained (language/vision) deep network
  • helpers/ has some helper functions for loading datasets, models, and features
  • language/ has some additional code for handling language models and datasets

To run the settings in our paper, you can use the following commands:

# Sentiment classification
python main.py --dataset sst --dataset-path   --dataset-type language --model-path barissayil/bert-sentiment-analysis-sst --arch bert --out-path ./tmp/sst/ --cache

# Toxic comment classification (biased)
python main.py --dataset jigsaw-toxic --dataset-path   --dataset-type language --model-path unitary/toxic-bert --arch bert --out-path ./tmp/jigsaw-toxic/ --cache --balance

# Toxic comment classification (unbiased)
python main.py --dataset jigsaw-alt-toxic --dataset-path   --dataset-type language --model-path unitary/unbiased-toxic-roberta --arch roberta --out-path ./tmp/unbiased-jigsaw-toxic/ --cache --balance

# Places-10 
python main.py --dataset places-10 --dataset-path  --dataset-type vision --model-path  --arch resnet50 --out-path ./tmp/places/ --cache

# ImageNet
python main.py --dataset imagenet --dataset-path  --dataset-type vision --model-path  --arch resnet50 --out-path ./tmp/imagenet/ --cache

Interpreting deep features

After fitting a sparse GLM with one of the above commands, we provide some notebooks for inspecting and visualizing the resulting features. See inspect_vision_models.ipynb and inspect_language_models.ipynb for the vision and language settings respectively.

Maintainers

Owner
Madry Lab
Towards a Principled Science of Deep Learning
Madry Lab
Adversarial Color Enhancement: Generating Unrestricted Adversarial Images by Optimizing a Color Filter

ACE Please find the preliminary version published at BMVC 2020 in the folder BMVC_version, and its extended journal version in Journal_version. Datase

28 Dec 25, 2022
Code for our work "Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection".

A2S-USOD Code for our work "Activation to Saliency: Forming High-Quality Labels for Unsupervised Salient Object Detection". Code will be released upon

15 Dec 16, 2022
DeepAL: Deep Active Learning in Python

DeepAL: Deep Active Learning in Python Python implementations of the following active learning algorithms: Random Sampling Least Confidence [1] Margin

Kuan-Hao Huang 583 Jan 03, 2023
Neural Turing Machines (NTM) - PyTorch Implementation

PyTorch Neural Turing Machine (NTM) PyTorch implementation of Neural Turing Machines (NTM). An NTM is a memory augumented neural network (attached to

Guy Zana 519 Dec 21, 2022
ML models and internal tensors 3D visualizer

The free Zetane Viewer is a tool to help understand and accelerate discovery in machine learning and artificial neural networks. It can be used to ope

Zetane Systems 787 Dec 30, 2022
This framework implements the data poisoning method found in the paper Adversarial Examples Make Strong Poisons

Adversarial poison generation and evaluation. This framework implements the data poisoning method found in the paper Adversarial Examples Make Strong

31 Nov 01, 2022
SenseNet is a sensorimotor and touch simulator for deep reinforcement learning research

SenseNet is a sensorimotor and touch simulator for deep reinforcement learning research

59 Feb 25, 2022
HiFT: Hierarchical Feature Transformer for Aerial Tracking (ICCV2021)

HiFT: Hierarchical Feature Transformer for Aerial Tracking Ziang Cao, Changhong Fu, Junjie Ye, Bowen Li, and Yiming Li Our paper is Accepted by ICCV 2

Intelligent Vision for Robotics in Complex Environment 55 Nov 23, 2022
PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in clustering (CVPR2021)

PiCIE: Unsupervised Semantic Segmentation using Invariance and Equivariance in Clustering Jang Hyun Cho1, Utkarsh Mall2, Kavita Bala2, Bharath Harihar

Jang Hyun Cho 164 Dec 30, 2022
Detection of PCBA defect

Detection_of_PCBA_defect Detection_of_PCBA_defect Use yolov5 to train. $pip install -r requirements.txt Detect.py will detect file(jpg,mp4...) in cu

6 Nov 28, 2022
Multi-Glimpse Network With Python

Multi-Glimpse Network Multi-Glimpse Network: A Robust and Efficient Classification Architecture based on Recurrent Downsampled Attention arXiv Require

9 May 10, 2022
A PyTorch implementation of "Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning", IJCAI-21

MERIT A PyTorch implementation of our IJCAI-21 paper Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning. Depen

Graph Analysis & Deep Learning Laboratory, GRAND 32 Jan 02, 2023
PyTorch code for training MM-DistillNet for multimodal knowledge distillation

There is More than Meets the Eye: Self-Supervised Multi-Object Detection and Tracking with Sound by Distilling Multimodal Knowledge MM-DistillNet is a

51 Dec 20, 2022
LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations

LIMEcraft LIMEcraft: Handcrafted superpixel selectionand inspection for Visual eXplanations The LIMEcraft algorithm is an explanatory method based on

MI^2 DataLab 4 Aug 01, 2022
Learning 3D Part Assembly from a Single Image

Learning 3D Part Assembly from a Single Image This repository contains a PyTorch implementation of the paper: Learning 3D Part Assembly from A Single

18 Dec 21, 2022
A machine learning malware analysis framework for Android apps.

🕵️ A machine learning malware analysis framework for Android apps. ☢️ DroidDetective is a Python tool for analysing Android applications (APKs) for p

James Stevenson 77 Dec 27, 2022
YOLOX Win10 Project

Introduction 这是一个用于Windows训练YOLOX的项目,相比于官方项目,做了一些适配和修改: 1、解决了Windows下import yolox失败,No such file or directory: 'xxx.xml'等路径问题 2、CUDA out of memory等显存不

5 Jun 08, 2022
This is an official implementation of the CVPR2022 paper "Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots".

Blind2Unblind: Self-Supervised Image Denoising with Visible Blind Spots Blind2Unblind Citing Blind2Unblind @inproceedings{wang2022blind2unblind, tit

demonsjin 58 Dec 06, 2022
Winners of DrivenData's Overhead Geopose Challenge

Winners of DrivenData's Overhead Geopose Challenge

DrivenData 22 Aug 04, 2022
StocksMA is a package to facilitate access to financial and economic data of Moroccan stocks.

Creating easier access to the Moroccan stock market data What is StocksMA ? StocksMA is a package to facilitate access to financial and economic data

Salah Eddine LABIAD 28 Jan 04, 2023