Black-box-Adversarial-Reprogramming
by yunyuntsai
Code for "Transfer Learning without Knowing: Reprogramming Black-box Machine Learning Models with Scarce Data and Limited Resources". (ICML 2020)
AI summary
Model reprogramming
An approach to adapt machine learning models using scarce data and limited resources by modifying their internal workings without changing the model's original architecture or training data.
- stars
- 37
- forks
- 4
- watching
- 3
Similar projects
Found by comparing what the projects do, not just their names.
Neural network reprogramming
Repurposes pre-trained neural networks for new classification tasks through adversarial reprogramming of their inputs.
Acoustic model reprogramming
An approach to reprogramming acoustic models for time series classification using differential mel-spectrograms and adversarial training
Network reprogramming
This project enables reprogramming of pre-trained neural networks to work on new tasks by fine-tuning them on smaller datasets.
Model reprogramming
Cross-modal Adversarial Reprogramming enables retraining of image models on text classification tasks
Memory optimizer for deep learning models
A lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution
ML toolbox
A toolkit for building and training machine learning models using a simple, easy-to-use interface.
Chinese NLU/NGL toolkit
This project provides pre-trained models and tools for natural language understanding (NLU) and generation (NLG) tasks in Chinese.
NLP toolkit
A collection of pre-trained language models for natural language processing tasks
Chinese language model fine-tuning tool
Improves pre-trained Chinese language models by incorporating a correction task to alleviate inconsistency issues with downstream tasks
ymcui/pert356
Semantic learning model
Develops a pre-trained language model to learn semantic knowledge from permuted text without mask labels
Speech Recognition
Developing low-resource speech command recognition systems using adversarial reprogramming and transfer learning
Vision-Language Learning Model
Develops and trains models for vision-language learning with decoupled language pre-training
ML reproducibility
A project demonstrating how to create a reproducible machine learning model using Python and version control
Retrieval model trainer
Trains and evaluates a universal multimodal retrieval model to perform various information retrieval tasks.
ML automator
Automates machine learning model training using pre-set configurations and modular design.
