code release for USENIX'22 paper `On the Security Risks of AutoML`

Related tags

Deep Learningautovul
Overview

This project is a minimized runnable project cut from trojanzoo, which contains more datasets, models, attacks and defenses. This repo will not be maintained.

This is a minimum code implementation of our USENIX'22 paper On the Security Risks of AutoML.

Abstract

The artifact discovers the vulnerability gap between manual models and automl models against various kinds of attacks (adversarial, poison, backdoor, extraction and membership) in image classification domain. It implements all datasets, models, and attacks used in our paper.
We expect the artifact could support the paper's claim that automl models are more vulnerable than manual models against various kinds of attacks, which could be explained by their small gradient variance.

Checklist

  • Binary: on pypi with any platform.
  • Model: ResNet and other model pretrained weights are available with --official flag to download them automatically at first running.
  • Data set: CIFAR10, CIFAR100 and ImageNet32.
    Use --download flag to download them automatically at first running.
    ImageNet32 requires manual set-up at their website due to legality.
  • Run-time environment:
    At any platform (Windows and Ubuntu tested).
    Pytorch and torchvision required. (CUDA recommended)
    adversarial-robustness-toolbox required for extraction attack and membership attack.
  • Hardware: GPU with CUDA support is recommended.
  • Execution: Model training and backdoor attack would be time-consuming. It would cost more than half day on a Nvidia Quodro RTX6000.
  • Metrics: Model accuracy, attack success rate, clean accuracy drop, cross entropy, f1 score, and auc.
  • Output: console output and saved model files (.pth).
  • Experiments: OS scripts.
  • How much disk space is required (approximately):
    less than 5GB.
  • How much time is needed to prepare workflow (approximately): within 1 hour.
  • How much time is needed to complete experiments (approximately): 3-4 days.
  • Publicly available: on GitHub.
  • Code licenses: GPL-3.
  • Archived: GitHub commit #XXXXXXX (todo).

Description

How to access

Hardware Dependencies

Recommend to use GPU with CUDA and CUDNN.
Less than 5GB disk space is needed.

Software Dependencies

You need to install python==3.9, pytorch==1.9.x, torchvision==0.10.x manually.

ART (IBM) required for extraction attack and membership attack.
pip install adversarial-robustness-toolbox

Data set

CIFAR10, CIFAR100 and ImageNet32.
Use --download flag to download them automatically at first running.
ImageNet32 requires manual set-up at their website due to legality.

Models

ResNet and other model pretrained weights are available with --official flag to download them automatically at first running.

Installation

(optional) Config Path

You can set the config files to customize data storage location and many other default settings. View /configs_example as an example config setting.
We support 3 configs (priority ascend):

  • package:
    (DO NOT MODIFY)
    autovul/base/configs/*.yml
    autovul/vision/configs/*.yml
  • user:
    ~/.autovul/configs/base/*.yml
    ~/.autovul/configs/vision/*.yml
  • workspace:
    ./configs/base/*.yml
    ./configs/vision/*.yml

Experiment Workflow

Bash Files

Check the bash files under /bash to reproduce our paper results.

Download Datasets

If you run it for the first time, please run bash ./bash/train.sh "--download" to download the dataset.

Train Models

You need to first run /bash/train.sh to get pretrained models.

Run Attacks

/bash/adv_attack.sh
/bash/poison.sh
/bash/backdoor.sh
/bash/extraction.sh
/bash/membership.sh

Run Other Exps

/bash/grad_var.sh
/bash/mitigation_backdoor.sh
/bash/mitigation_extraction.sh

For mitigation experiments, the architecture names in our paper map to:

  • darts-i : diy_deep
  • darts-ii : diy_no_skip
  • darts-iii: diy_deep_noskip

These are the 3 options for --model_arch {arch} (with --model darts)

Evaluation and Expected Result

Our paper claims that automl models are more vulnerable than manual models against various kinds of attacks, which could be explained by low gradient variance. Therefore, for each attack, we expect automl models to have:

Train

Most models around 96%-97% accuracy on CIFAR10.

Attack

For automl models on CIFAR10,

  • adversarial
    higher success rate (around 10%).
  • poison
    lower accuracy drop (around 5%).
  • backdoor
    higher success rate (around 2%) lower accuracy drop (around 1%).
  • extraction
    lower inference cross entropy (around 0.3).
  • membership
    higher auc (around 0.04).

Others

  • gradient variance
    automl with lower gradient variance (around 2.2).
  • mitigation architecture
    deep architectures (darts-i, darts-iii) have larger cross entropy for extraction attack (around 0.5), and higher accuracy drop for poisoning attack (around 7%).

Experiment Customization

Use -h or --help flag for example python files to check available arguments.

Comments
  • Bump docker/build-push-action from 2.7.0 to 2.8.0

    Bump docker/build-push-action from 2.7.0 to 2.8.0

    Bumps docker/build-push-action from 2.7.0 to 2.8.0.

    Release notes

    Sourced from docker/build-push-action's releases.

    v2.8.0

    • Allow specifying subdirectory with default git context (#531)
    • Add cgroup-parent, shm-size, ulimit inputs (#501)
    • Don't set outputs if empty or nil (#470)
    • docs: example to sanitize tags with metadata-action (#476)
    • docs: wrong syntax to sanitize repo slug (#475)
    • docs: test before pushing your image (#455)
    • readme: remove v1 section (#500)
    • ci: virtual env file system info (#510)
    • dev: update workflow (#499)
    • Bump @​actions/core from 1.5.0 to 1.6.0 (#160)
    • Bump ansi-regex from 5.0.0 to 5.0.1 (#469)
    • Bump tmpl from 1.0.4 to 1.0.5 (#465)
    • Bump csv-parse from 4.16.0 to 4.16.3 (#451 #459)
    Commits
    • 1814d3d Merge pull request #531 from BeyondEvil/subdir-with-default-context
    • fc5a732 Add subdirectory for Git context
    • b1aeb11 Merge pull request #510 from crazy-max/venv
    • e31f93a ci: virtual env file system info
    • 9ed5823 Merge pull request #501 from crazy-max/new-inputs
    • 4222161 Merge pull request #500 from crazy-max/readme
    • 67ff4df add cgroup-parent, shm-size, ulimit inputs
    • 91274a0 sort flags
    • ff32939 readme: remove v1 section
    • 04841f2 Merge pull request #499 from crazy-max/update-workflow
    • Additional commits viewable in compare view

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    dependencies github_actions 
    opened by dependabot[bot] 1
  • Bump docker/login-action from 1.10.0 to 1.12.0

    Bump docker/login-action from 1.10.0 to 1.12.0

    Bumps docker/login-action from 1.10.0 to 1.12.0.

    Release notes

    Sourced from docker/login-action's releases.

    v1.12.0

    • ECR: only set credentials if username and password are specified (#128)
    • Refactor to use aws-sdk v3 (#128)

    v1.11.0

    • ECR: switch implementation to use the AWS SDK (#126)
    • ecr input to specify whether the given registry is ECR (#123)
    • Test against Windows runner (#126)
    • Update instructions for Google registry (#127)
    • Update dev workflow (#111)
    • Small changes for GHCR doc (#86)
    • Update dev dependencies (#85)
    • Bump ansi-regex from 5.0.0 to 5.0.1 (#101)
    • Bump tmpl from 1.0.4 to 1.0.5 (#100)
    • Bump @​actions/core from 1.4.0 to 1.6.0 (#94 #103)
    • Bump codecov/codecov-action from 1 to 2 (#88)
    • Bump hosted-git-info from 2.8.8 to 2.8.9 (#83)
    • Bump node-notifier from 8.0.0 to 8.0.2 (#82)
    • Bump ws from 7.3.1 to 7.5.0 (#81)
    • Bump lodash from 4.17.20 to 4.17.21 (#80)
    • Bump y18n from 4.0.0 to 4.0.3 (#79)
    Commits
    • 42d299f Merge pull request #130 from crazy-max/ci-workflow
    • 4858b0b Update ci workflow
    • 1d7d864 Merge pull request #128 from Flydiverny/aws-sdk-v3
    • 5885569 refactor: use v3 sdk
    • d9927c4 Merge pull request #123 from crazy-max/ecr-input
    • b9a4d91 ecr input to specify whether the given registry is ECR
    • b20b9f5 Merge pull request #126 from crazy-max/aws-sdk
    • cb21399 ci: test against windows runner
    • faae4d6 ecr: switch implementation to use the AWS SDK
    • 4d84a3c Merge pull request #127 from crazy-max/carry-124
    • Additional commits viewable in compare view

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    dependencies github_actions 
    opened by dependabot[bot] 0
  • Bump docker/login-action from 1.12.0 to 1.13.0

    Bump docker/login-action from 1.12.0 to 1.13.0

    Bumps docker/login-action from 1.12.0 to 1.13.0.

    Release notes

    Sourced from docker/login-action's releases.

    v1.13.0

    • Handle proxy settings for aws-sdk (#152)
    • Workload identity based authentication docs for GCR and GAR (#112)
    • Test login against ACR (#49)
    • Bump @​aws-sdk/client-ecr from 3.44.0 to 3.45.0 (#132)
    • Bump @​aws-sdk/client-ecr-public from 3.43.0 to 3.45.0 (#131)
    Commits
    • 6af3c11 Merge pull request #152 from crazy-max/aws-sdk-proxy
    • caca336 handle proxy settings for aws-sdk
    • 17f28ab Merge pull request #112 from dineshba/workload-identity-gcr-gar
    • a875dd0 Update readme with workload identity based authentication for GCR and GAR
    • 7948fff Merge pull request #49 from crazy-max/e2e-acr
    • 5fcefb9 Merge pull request #131 from docker/dependabot/npm_and_yarn/aws-sdk/client-ec...
    • 3bb2d08 Update generated content
    • 242fb9a Bump @​aws-sdk/client-ecr-public from 3.43.0 to 3.45.0
    • fa72313 Merge pull request #132 from docker/dependabot/npm_and_yarn/aws-sdk/client-ec...
    • 088f62a Update generated content
    • Additional commits viewable in compare view

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    dependencies github_actions 
    opened by dependabot[bot] 0
  • Bump actions/github-script from 5 to 6

    Bump actions/github-script from 5 to 6

    Bumps actions/github-script from 5 to 6.

    Release notes

    Sourced from actions/github-script's releases.

    v6.0.0

    What's Changed

    Breaking Changes

    With the update to Node 16 in #235, all scripts will now be run with Node 16 rather than Node 12.

    New Contributors

    Full Changelog: https://github.com/actions/github-script/compare/v5...v6.0.0

    v5.1.0

    What's Changed

    New Contributors

    Full Changelog: https://github.com/actions/github-script/compare/v5.0.0...v5.1.0

    Commits
    • 9ac0880 Merge pull request #240 from actions/joshmgross/document-esm
    • 53cdbb4 Merge pull request #239 from actions/joshmgross/v6
    • 6b8d8aa Merge pull request #238 from actions/joshmgross/update-actions-core
    • 6689be4 Merge pull request #237 from actions/joshmgross/audit-fix
    • 5541733 Add an example using ESM import
    • cd8eebf Release version 6.0.0
    • 72fadf4 Update @actions/core to 1.6.0
    • d526c04 Update node-fetch license
    • 2c946f1 Run npm audit fix
    • 41e1ab4 Merge pull request #235 from thboop/patch-1
    • Additional commits viewable in compare view

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    dependencies github_actions 
    opened by dependabot[bot] 0
  • Bump docker/build-push-action from 2.7.0 to 2.9.0

    Bump docker/build-push-action from 2.7.0 to 2.9.0

    Bumps docker/build-push-action from 2.7.0 to 2.9.0.

    Release notes

    Sourced from docker/build-push-action's releases.

    v2.9.0

    • add-hosts input (#553 #555)
    • Fix git context subdir example and improve README (#552)
    • Add e2e tests for ACR (#548)
    • Add description on github-token option to README (#544)
    • Bump node-fetch from 2.6.1 to 2.6.7 (#549)

    v2.8.0

    • Allow specifying subdirectory with default git context (#531)
    • Add cgroup-parent, shm-size, ulimit inputs (#501)
    • Don't set outputs if empty or nil (#470)
    • docs: example to sanitize tags with metadata-action (#476)
    • docs: wrong syntax to sanitize repo slug (#475)
    • docs: test before pushing your image (#455)
    • readme: remove v1 section (#500)
    • ci: virtual env file system info (#510)
    • dev: update workflow (#499)
    • Bump @​actions/core from 1.5.0 to 1.6.0 (#160)
    • Bump ansi-regex from 5.0.0 to 5.0.1 (#469)
    • Bump tmpl from 1.0.4 to 1.0.5 (#465)
    • Bump csv-parse from 4.16.0 to 4.16.3 (#451 #459)
    Commits
    • 7f9d37f Merge pull request #555 from crazy-max/fix-add-host
    • d745845 Fix add-hosts context
    • 1ca185b Merge pull request #553 from crazy-max/add-host
    • eebf87a add-host input
    • d8b0ca6 Merge pull request #552 from crazy-max/readme
    • da76737 Fix git context subdir example and improve README
    • 8c76bb7 Merge pull request #549 from docker/dependabot/npm_and_yarn/node-fetch-2.6.7
    • b598b2a Update generated content
    • eb2857f Bump node-fetch from 2.6.1 to 2.6.7
    • f4cf574 Merge pull request #548 from crazy-max/e2e-acr
    • Additional commits viewable in compare view

    Dependabot compatibility score

    Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.


    Dependabot commands and options

    You can trigger Dependabot actions by commenting on this PR:

    • @dependabot rebase will rebase this PR
    • @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
    • @dependabot merge will merge this PR after your CI passes on it
    • @dependabot squash and merge will squash and merge this PR after your CI passes on it
    • @dependabot cancel merge will cancel a previously requested merge and block automerging
    • @dependabot reopen will reopen this PR if it is closed
    • @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
    • @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
    • @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
    dependencies github_actions 
    opened by dependabot[bot] 0
  • Reproduction of Attack Effectiveness of Membership Inference Attacks

    Reproduction of Attack Effectiveness of Membership Inference Attacks

    Thanks for sharing the source code of your excellent work!

    I tried to reproduce the experimental results of label-only membership inference attacks against various architectures in your paper. Here I followed the parameter settings in your paper (see Appendix B for more details) and the parameter settings in membership.py were modified as follows:

    max_iter = 50
    max_eval = 2500
    sample_size = 1000
    init_size = 100
    init_eval = 100
    

    And also, I used your pretrained models from Google Drive to conduct the experiments on the CIFAR10 dataset. The experimental results on the CIFAR10 dataset are shown below.

    |Architecture|AUC| |:-:|:-:| |BiT|0.5392| |DenseNet|0.5141| |DLA|0.5060| |ResNet|0.5049| |ResNext|0.5043| |VGG|0.6070| |WideResnet|0.5352| |AmoebaNet|0.5029| |DARTS|0.5220| |DrNAS|0.5192| |ENAS|0.5069| |NASNet|0.5285| |PC-DARTS|0.5087| |PDARTS|0.5271| |SGAS|0.5038| |SNAS|0.5081| |Random|0.5023|

    However, the experimental results show a phenomenon contrary to what you present in your paper, i.e., the manual architectures seem to be more vulnerable to membership inference attacks than the NAS architectures.

    Is there anything wrong with my parameter settings (I only modified the default parameter settings of membership.py in my experiments)? Or, do I need anything more to reproduce the experimental results of your paper?

    Thanks in advance!

    opened by MiracleHH 0
Owner
Ren Pang
Ren Pang, PhD at Penn State IST. Working on deep learning security about adversarial and backdoor attacks/defenses.
Ren Pang
Framework for Spectral Clustering on the Sparse Coefficients of Learned Dictionaries

Dictionary Learning for Clustering on Hyperspectral Images Overview Framework for Spectral Clustering on the Sparse Coefficients of Learned Dictionari

Joshua Bruton 6 Oct 25, 2022
A smaller subset of 10 easily classified classes from Imagenet, and a little more French

Imagenette 🎶 Imagenette, gentille imagenette, Imagenette, je te plumerai. 🎶 (Imagenette theme song thanks to Samuel Finlayson) NB: Versions of Image

fast.ai 718 Jan 01, 2023
Adjust Decision Boundary for Class Imbalanced Learning

Adjusting Decision Boundary for Class Imbalanced Learning This repository is the official PyTorch implementation of WVN-RS, introduced in Adjusting De

Peyton Byungju Kim 16 Jan 04, 2023
WarpRNNT loss ported in Numba CPU/CUDA for Pytorch

RNNT loss in Pytorch - Numba JIT compiled (warprnnt_numba) Warp RNN Transducer Loss for ASR in Pytorch, ported from HawkAaron/warp-transducer and a re

Somshubra Majumdar 15 Oct 22, 2022
Official Repo for ICCV2021 Paper: Learning to Regress Bodies from Images using Differentiable Semantic Rendering

[ICCV2021] Learning to Regress Bodies from Images using Differentiable Semantic Rendering Getting Started DSR has been implemented and tested on Ubunt

Sai Kumar Dwivedi 83 Nov 27, 2022
A whale detector design for the Kaggle whale-detector challenge!

CNN (InceptionV1) + STFT based Whale Detection Algorithm So, this repository is my PyTorch solution for the Kaggle whale-detection challenge. The obje

Tarin Ziyaee 92 Sep 28, 2021
Gesture Volume Control Using OpenCV and MediaPipe

This Project Uses OpenCV and MediaPipe Hand solutions to identify hands and Change system volume by taking thumb and index finger positions

Pratham Bhatnagar 6 Sep 12, 2022
An evaluation toolkit for voice conversion models.

Voice-conversion-evaluation An evaluation toolkit for voice conversion models. Sample test pair Generate the metadata for evaluating models. The direc

30 Aug 29, 2022
Checking fibonacci - Generating the Fibonacci sequence is a classic recursive problem

Fibonaaci Series Generating the Fibonacci sequence is a classic recursive proble

Moureen Caroline O 1 Feb 15, 2022
基于DouZero定制AI实战欢乐斗地主

DouZero_For_Happy_DouDiZhu: 将DouZero用于欢乐斗地主实战 本项目基于DouZero 环境配置请移步项目DouZero 模型默认为WP,更换模型请修改start.py中的模型路径 运行main.py即可 SL (baselines/sl/): 基于人类数据进行深度学习

1.5k Jan 08, 2023
PySlowFast: video understanding codebase from FAIR for reproducing state-of-the-art video models.

PySlowFast PySlowFast is an open source video understanding codebase from FAIR that provides state-of-the-art video classification models with efficie

Meta Research 5.3k Jan 03, 2023
The repo of Feedback Networks, CVPR17

Feedback Networks http://feedbacknet.stanford.edu/ Paper: Feedback Networks, CVPR 2017. Amir R. Zamir*,Te-Lin Wu*, Lin Sun, William B. Shen, Bertram E

Stanford Vision and Learning Lab 87 Nov 19, 2022
cisip-FIRe - Fast Image Retrieval

Fast Image Retrieval (FIRe) is an open source image retrieval project release by Center of Image and Signal Processing Lab (CISiP Lab), Universiti Malaya. This project implements most of the major bi

CISiP Lab 39 Nov 25, 2022
LaneAF: Robust Multi-Lane Detection with Affinity Fields

LaneAF: Robust Multi-Lane Detection with Affinity Fields This repository contains Pytorch code for training and testing LaneAF lane detection models i

155 Dec 17, 2022
Person Re-identification

Person Re-identification Final project of Computer Vision Table of content Person Re-identification Table of content Students: Proposed method Dataset

Nguyễn Hoàng Quân 4 Jun 17, 2021
This is the repository for our paper SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking

SimpleTrack This is the repository for our paper SimpleTrack: Understanding and Rethinking 3D Multi-object Tracking. We are still working on writing t

TuSimple 189 Dec 26, 2022
Python implementation of NARS (Non-Axiomatic-Reasoning-System)

Python implementation of NARS (Non-Axiomatic-Reasoning-System)

Bowen XU 11 Dec 20, 2022
A PyTorch implementation of "DGC-Net: Dense Geometric Correspondence Network"

DGC-Net: Dense Geometric Correspondence Network This is a PyTorch implementation of our work "DGC-Net: Dense Geometric Correspondence Network" TL;DR A

191 Dec 16, 2022
Implementation of "Glancing Transformer for Non-Autoregressive Neural Machine Translation"

GLAT Implementation for the ACL2021 paper "Glancing Transformer for Non-Autoregressive Neural Machine Translation" Requirements Python = 3.7 Pytorch

117 Jan 09, 2023
PyTorch implementation of "Transparency by Design: Closing the Gap Between Performance and Interpretability in Visual Reasoning"

Transparency-by-Design networks (TbD-nets) This repository contains code for replicating the experiments and visualizations from the paper Transparenc

David Mascharka 351 Nov 18, 2022