Transfer-Learning-Library
AugMax
Transfer-Learning-Library | AugMax | |
---|---|---|
1 | 3 | |
3,150 | 122 | |
2.2% | 0.0% | |
6.9 | 0.0 | |
about 1 month ago | over 2 years ago | |
Python | Python | |
MIT License | MIT License |
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.
Transfer-Learning-Library
-
[R] pytorch library for audio/speech domain adaptation?
Are there any pytorch libraries to do benchmarking of domain adaptation methods for audio/speech tasks? Something like the Transfer Learning Library (https://github.com/thuml/Transfer-Learning-Library/) for images.
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
What are some alternatives?
TranAD - [VLDB'22] Anomaly Detection using Transformers, self-conditioning and adversarial training.
advertorch - A Toolbox for Adversarial Robustness Research
DeepLabCut - Official implementation of DeepLabCut: Markerless pose estimation of user-defined features with deep learning for all animals incl. humans
Awesome-Out-Of-Distribution-Detection - A professionally curated list of papers, tutorials, books, videos, articles and open-source libraries etc for Out-of-distribution detection, robustness, and generalization
transferlearning - Transfer learning / domain adaptation / domain generalization / multi-task learning etc. Papers, codes, datasets, applications, tutorials.-迁移学习
CEPC - A domain adaptation model
AdaTime - [TKDD 2023] AdaTime: A Benchmarking Suite for Domain Adaptation on Time Series Data
StyleDomain - Official Implementation for "StyleDomain: Efficient and Lightweight Parameterizations of StyleGAN for One-shot and Few-shot Domain Adaptation" (ICCV 2023)
pytorch-adapt - Domain adaptation made easy. Fully featured, modular, and customizable.
DA-Faster-RCNN - Detectron2 implementation of DA-Faster R-CNN, Domain Adaptive Faster R-CNN for Object Detection in the Wild