Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

Last update: Oct 28, 2022

Related tags

Deep Learning Contra-OOD

Overview

Contra-OOD

Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

Requirements

PyTorch
Transformers
datasets
wandb
tqdm
scikit-learn

Dataset

Most datasets used in paper are automatically downloaded by the datasets package. Instructions on downloading sst2 and multi30k are provided in readme.txt under the data folder.

Training and Evaluation

Finetune the PLM with the following command:

>> python run.py --task_name task

The task_name parameter can take sst2, imdb, trec, or 20ng. The training loss and evaluation results on the test set are synced to the wandb dashboard.

Owner

Wenxuan Zhou

Ph.D. student at University of Southern California

GitHub Repository

Fibonacci Method Gradient Descent

An implementation of the Fibonacci method for gradient descent, featuring a TKinter GUI for inputting the function / parameters to be examined and a matplotlib plot of the function and results.

1 Jan 28, 2022

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

One Pixel Attack How simple is it to cause a deep neural network to misclassify an image if an attacker is only allowed to modify the color of one pix

1.2k Dec 26, 2022

Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

Related tags

Overview

Contra-OOD

Requirements

Dataset

Training and Evaluation

Owner

Wenxuan Zhou

Fibonacci Method Gradient Descent

Keras implementation of "One pixel attack for fooling deep neural networks" using differential evolution on Cifar10 and ImageNet

Repository providing a wide range of self-supervised pretrained models for computer vision tasks.

Python implementation of "Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation"

Duke Machine Learning Winter School: Computer Vision 2022

Tool which allow you to detect and translate text.

Official implementation of "Generating 3D Molecules for Target Protein Binding"

Deepfake Scanner by Deepware.

Transfer Reinforcement Learning for Differing Action Spaces via Q-Network Representations

Sample Prior Guided Robust Model Learning to Suppress Noisy Labels

Pure python PEMDAS expression solver without using built-in eval function

This dlib-based facial login system

This is a custom made virus code in python, using tkinter module.

Source code for GNN-LSPE (Graph Neural Networks with Learnable Structural and Positional Representations)

OSLO: Open Source framework for Large-scale transformer Optimization

Monocular 3D Object Detection: An Extrinsic Parameter Free Approach (CVPR2021)

Orthogonal Over-Parameterized Training

Simple data balancing baselines for worst-group-accuracy benchmarks.

NAVER BoostCamp Final Project

A developer interface for creating Chat AIs for the Chai app.