ASTRASelf-training with Weak Supervision (NAACL 2021)
Stars: ✭ 127 (+8.55%)
WeFEND-AAAI20Dataset for paper "Weak Supervision for Fake News Detection via Reinforcement Learning" published in AAAI'2020.
Stars: ✭ 67 (-42.74%)
knodleA PyTorch-based open-source framework that provides methods for improving the weakly annotated data and allows researchers to efficiently develop and compare their own methods.
Stars: ✭ 76 (-35.04%)
wrenchWRENCH: Weak supeRvision bENCHmark
Stars: ✭ 185 (+58.12%)
concept-based-xaiLibrary implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (-64.96%)
troveWeakly supervised medical named entity classification
Stars: ✭ 55 (-52.99%)
Learning-From-RulesImplementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net/forum?id=SkeuexBtDr)
Stars: ✭ 46 (-60.68%)
weak-supervision-for-NERFramework to learn Named Entity Recognition models without labelled data using weak supervision.
Stars: ✭ 114 (-2.56%)
ConSSLPyTorch Implementation of SOTA SSL methods
Stars: ✭ 61 (-47.86%)
hamnetPyTorch implementation of AAAI 2021 paper: A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization
Stars: ✭ 30 (-74.36%)
WSL4MISScribbles or Points-based weakly-supervised learning for medical image segmentation, a strong baseline, and tutorial for research and application.
Stars: ✭ 100 (-14.53%)
spearSPEAR: Programmatically label and build training data quickly.
Stars: ✭ 81 (-30.77%)
deepfillv2-pylightningClean minimal implementation of Free-Form Image Inpainting with Gated Convolutions in pytorch lightning. Inspired from pytorch implementation by @avalonstrel.
Stars: ✭ 13 (-88.89%)
WeSTClass[CIKM 2018] Weakly-Supervised Neural Text Classification
Stars: ✭ 67 (-42.74%)
AutoTabularAutomatic machine learning for tabular data. ⚡🔥⚡
Stars: ✭ 51 (-56.41%)
WS3DOfficial version of 'Weakly Supervised 3D object detection from Lidar Point Cloud'(ECCV2020)
Stars: ✭ 104 (-11.11%)
Pontryagin-Differentiable-ProgrammingA unified end-to-end learning and control framework that is able to learn a (neural) control objective function, dynamics equation, control policy, or/and optimal trajectory in a control system.
Stars: ✭ 111 (-5.13%)
just-ask[TPAMI Special Issue on ICCV 2021 Best Papers, Oral] Just Ask: Learning to Answer Questions from Millions of Narrated Videos
Stars: ✭ 57 (-51.28%)
MetaCatMinimally Supervised Categorization of Text with Metadata (SIGIR'20)
Stars: ✭ 52 (-55.56%)
RSC-NetImplementation for "3D human pose, shape and texture from low-resolution images and videos", TPAMI 2021
Stars: ✭ 43 (-63.25%)
TS-CAMCodes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.
Stars: ✭ 96 (-17.95%)
Awesome-Weak-Shot-LearningA curated list of papers, code and resources pertaining to weak-shot classification, detection, and segmentation.
Stars: ✭ 142 (+21.37%)
Transformer-QG-on-SQuADImplement Question Generator with SOTA pre-trained Language Models (RoBERTa, BERT, GPT, BART, T5, etc.)
Stars: ✭ 28 (-76.07%)
deviation-networkSource code of the KDD19 paper "Deep anomaly detection with deviation networks", weakly/partially supervised anomaly detection, few-shot anomaly detection
Stars: ✭ 94 (-19.66%)
lightning-hydra-templatePyTorch Lightning + Hydra. A very user-friendly template for rapid and reproducible ML experimentation with best practices. ⚡🔥⚡
Stars: ✭ 1,905 (+1528.21%)
VideoTransformer-pytorchPyTorch implementation of a collections of scalable Video Transformer Benchmarks.
Stars: ✭ 159 (+35.9%)
C2CImplementation of Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification approach.
Stars: ✭ 30 (-74.36%)
map-floodwater-satellite-imageryThis repository focuses on training semantic segmentation models to predict the presence of floodwater for disaster prevention. Models were trained using SageMaker and Colab.
Stars: ✭ 21 (-82.05%)
MCIS wsssCode for ECCV 2020 paper (oral): Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Stars: ✭ 151 (+29.06%)
QuantumForestFast Differentiable Forest lib with the advantages of both decision trees and neural networks
Stars: ✭ 63 (-46.15%)
hififaceUnofficial PyTorch Implementation for HifiFace (https://arxiv.org/abs/2106.09965)
Stars: ✭ 227 (+94.02%)
WSCNNTDSaliency[BMVC17] Weakly Supervised Saliency Detection with A Category-Driven Map Generator
Stars: ✭ 19 (-83.76%)
BrainMaGeBrain extraction in presence of abnormalities, using single and multiple MRI modalities
Stars: ✭ 23 (-80.34%)
RIBReducing Information Bottleneck for Weakly Supervised Semantic Segmentation (NeurIPS 2021)
Stars: ✭ 40 (-65.81%)
Fast-AgingGANA deep learning model to age faces in the wild, currently runs at 60+ fps on GPUs
Stars: ✭ 133 (+13.68%)
HiGitClassHiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories (ICDM'19)
Stars: ✭ 58 (-50.43%)
WSDECWeakly Supervised Dense Event Captioning in Videos, i.e. generating multiple sentence descriptions for a video in a weakly-supervised manner.
Stars: ✭ 95 (-18.8%)
GAL-fWSDGenerative Adversarial Learning Towards Fast Weakly Supervised Detection
Stars: ✭ 18 (-84.62%)
hydra-zenPythonic functions for creating and enhancing Hydra applications
Stars: ✭ 165 (+41.03%)
Learning-Action-Completeness-from-PointsOfficial Pytorch Implementation of 'Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization' (ICCV-21 Oral)
Stars: ✭ 53 (-54.7%)
skillful nowcastingImplementation of DeepMind's Deep Generative Model of Radar (DGMR) https://arxiv.org/abs/2104.00954
Stars: ✭ 117 (+0%)
DiscoBoxThe Official PyTorch Implementation of DiscoBox.
Stars: ✭ 95 (-18.8%)
uvadlc notebooksRepository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2022/Spring 2022
Stars: ✭ 901 (+670.09%)
SPMLUniversal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning
Stars: ✭ 81 (-30.77%)
reefAutomatically labeling training data
Stars: ✭ 102 (-12.82%)
WeSHClass[AAAI 2019] Weakly-Supervised Hierarchical Text Classification
Stars: ✭ 83 (-29.06%)
labml🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱
Stars: ✭ 1,213 (+936.75%)
pytorch-lightning-templateAn easy/swift-to-adapt PyTorch-Lighting template. 套壳模板,简单易用,稍改原来Pytorch代码,即可适配Lightning。You can translate your previous Pytorch code much easier using this template, and keep your freedom to edit all the functions as well. Big-project-friendly as well.
Stars: ✭ 555 (+374.36%)
CleanlabThe standard package for machine learning with noisy labels, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.
Stars: ✭ 2,526 (+2058.97%)
capsule-sample-space-resortsThe Space Resorts sample capsule demonstrates a fully-developed capsule that uses several of the features and abilities discussed in the Bixby Developer Guides, while also using the best practices described in the Bixby Design Guides.
Stars: ✭ 24 (-79.49%)
SnorkelA system for quickly generating training data with weak supervision
Stars: ✭ 4,953 (+4133.33%)