SELFIE

Data refinement method

A method to enhance robustness in deep learning by selectively refining noisy training data and combining it with clean samples.

GitHub

50 stars
7 watching
9 forks
Language: Python
last commit: over 6 years ago

Related projects:

RepositoryDescriptionStars
hendrycks/robustnessEvaluates and benchmarks the robustness of deep learning models to various corruptions and perturbations in computer vision tasks.1,030
rentruewang/koilaA lightweight wrapper around PyTorch to prevent CUDA out-of-memory errors and optimize model execution1,823
nitishsrivastava/deepnetA collection of GPU-accelerated deep learning algorithms implemented in Python895
davisyoshida/loraxA JAX transform that simplifies the training of large language models by reducing memory usage through low-rank adaptation.134
rksltnl/deep-metric-learning-cvpr16A software framework for building deep metric learning models using lifted structured feature embedding346
ardavans/dsrAn algorithm for deep reinforcement learning that combines model-free and model-based approaches to learn robust value functions.98
qingyonghu/randla-netA deep learning framework for efficient semantic segmentation of large-scale 3D point clouds1,327
deependersingla/deep_portfolioAn algorithm that optimizes portfolio allocation using Reinforcement Learning and Supervised learning.168
abbypa/nnproject_deepmaskA deep learning implementation of an object segmentation algorithm.187
xternalz/sdpointA deep learning method for optimizing convolutional neural networks by reducing computational cost while improving regularization and inference efficiency.18
rozumden/defmoA deep learning framework for deblurring and recovering the shape of fast-moving objects from blurred images171
zwyking/fast-stabThis project provides an implementation of video stabilization with iterative optimization using deep learning techniques.34
wasidennis/deepharmonizationReimplements a deep learning model to harmonize images from different illumination conditions150
nust-machine-intelligence-laboratory/jo-srcAn implementation of a contrastive learning approach to address noisy labels in machine learning models5
autodistill/autodistillAutomatically trains models from large foundation models to perform specific tasks with minimal human intervention.2,022