AugMax
Awesome-Out-Of-Distribution-Detection
AugMax | Awesome-Out-Of-Distribution-Detection | |
---|---|---|
3 | 6 | |
122 | 551 | |
0.0% | - | |
0.0 | 7.6 | |
over 2 years ago | 15 days ago | |
Python | ||
MIT License | Creative Commons Zero v1.0 Universal |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
AugMax
-
[R] [2110.13771] AugMax: Adversarial Composition of Random Augmentations for Robust Training
Abstract: Data augmentation is a simple yet effective way to improve the robustness of deep neural networks (DNNs). Diversity and hardness are two complementary dimensions of data augmentation to achieve robustness. For example, AugMix explores random compositions of a diverse set of augmentations to enhance broader coverage, while adversarial training generates adversarially hard samples to spot the weakness. Motivated by this, we propose a data augmentation framework, termed AugMax, to unify the two aspects of diversity and hardness. AugMax first randomly samples multiple augmentation operators and then learns an adversarial mixture of the selected operators. Being a stronger form of data augmentation, AugMax leads to a significantly augmented input distribution which makes model training more challenging. To solve this problem, we further design a disentangled normalization module, termed DuBIN (Dual-Batch-and-Instance Normalization), that disentangles the instance-wise feature heterogeneity arising from AugMax. Experiments show that AugMax-DuBIN leads to significantly improved out-of-distribution robustness, outperforming prior arts by 3.03%, 3.49%, 1.82% and 0.71% on CIFAR10-C, CIFAR100-C, Tiny ImageNet-C and ImageNet-C. Codes and pretrained models are available: this https URL.
-
Researchers Introduce ‘AugMax’: An Open-Sourced Data Augmentation Framework To Unify The Two Aspects Of Diversity And Hardness
Code for https://arxiv.org/abs/2110.13771 found: https://github.com/VITA-Group/AugMax
Paper | Github | Quick 2 Min Read
Awesome-Out-Of-Distribution-Detection
What are some alternatives?
advertorch - A Toolbox for Adversarial Robustness Research
awesome-ocr
Transfer-Learning-Library - Transfer Learning Library for Domain Adaptation, Task Adaptation, and Domain Generalization
best-of-jupyter - 🏆 A ranked list of awesome Jupyter Notebook, Hub and Lab projects (extensions, kernels, tools). Updated weekly.
TranAD - [VLDB'22] Anomaly Detection using Transformers, self-conditioning and adversarial training.
Awesome-pytorch-list - A comprehensive list of pytorch related content on github,such as different models,implementations,helper libraries,tutorials etc.
awesome-python-data-science - Probably the best curated list of data science software in Python.
yt-channels-DS-AI-ML-CS - A comprehensive list of 180+ YouTube Channels for Data Science, Data Engineering, Machine Learning, Deep learning, Computer Science, programming, software engineering, etc.
datascience - Curated list of Python resources for data science.
500-AI-Machine-learning-Deep-learning-Computer-vision-NLP-Projects-with-code - 500 AI Machine learning Deep learning Computer vision NLP Projects with code