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 (-40.16%)
troveWeakly supervised medical named entity classification
Stars: ✭ 55 (-56.69%)
weaselWeakly Supervised End-to-End Learning (NeurIPS 2021)
Stars: ✭ 117 (-7.87%)
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 (-63.78%)
concept-based-xaiLibrary implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI
Stars: ✭ 41 (-67.72%)
wrenchWRENCH: Weak supeRvision bENCHmark
Stars: ✭ 185 (+45.67%)
WeFEND-AAAI20Dataset for paper "Weak Supervision for Fake News Detection via Reinforcement Learning" published in AAAI'2020.
Stars: ✭ 67 (-47.24%)
just-ask[TPAMI Special Issue on ICCV 2021 Best Papers, Oral] Just Ask: Learning to Answer Questions from Millions of Narrated Videos
Stars: ✭ 57 (-55.12%)
GAL-fWSDGenerative Adversarial Learning Towards Fast Weakly Supervised Detection
Stars: ✭ 18 (-85.83%)
MetaCatMinimally Supervised Categorization of Text with Metadata (SIGIR'20)
Stars: ✭ 52 (-59.06%)
Learning-Action-Completeness-from-PointsOfficial Pytorch Implementation of 'Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization' (ICCV-21 Oral)
Stars: ✭ 53 (-58.27%)
TS-CAMCodes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.
Stars: ✭ 96 (-24.41%)
spearSPEAR: Programmatically label and build training data quickly.
Stars: ✭ 81 (-36.22%)
Awesome-Weak-Shot-LearningA curated list of papers, code and resources pertaining to weak-shot classification, detection, and segmentation.
Stars: ✭ 142 (+11.81%)
deviation-networkSource code of the KDD19 paper "Deep anomaly detection with deviation networks", weakly/partially supervised anomaly detection, few-shot anomaly detection
Stars: ✭ 94 (-25.98%)
SPMLUniversal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning
Stars: ✭ 81 (-36.22%)
hamnetPyTorch implementation of AAAI 2021 paper: A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization
Stars: ✭ 30 (-76.38%)
C2CImplementation of Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification approach.
Stars: ✭ 30 (-76.38%)
WeSHClass[AAAI 2019] Weakly-Supervised Hierarchical Text Classification
Stars: ✭ 83 (-34.65%)
WSDECWeakly Supervised Dense Event Captioning in Videos, i.e. generating multiple sentence descriptions for a video in a weakly-supervised manner.
Stars: ✭ 95 (-25.2%)
WS3DOfficial version of 'Weakly Supervised 3D object detection from Lidar Point Cloud'(ECCV2020)
Stars: ✭ 104 (-18.11%)
WSL4MISScribbles or Points-based weakly-supervised learning for medical image segmentation, a strong baseline, and tutorial for research and application.
Stars: ✭ 100 (-21.26%)
RSC-NetImplementation for "3D human pose, shape and texture from low-resolution images and videos", TPAMI 2021
Stars: ✭ 43 (-66.14%)
DiscoBoxThe Official PyTorch Implementation of DiscoBox.
Stars: ✭ 95 (-25.2%)
reefAutomatically labeling training data
Stars: ✭ 102 (-19.69%)
MCIS wsssCode for ECCV 2020 paper (oral): Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation
Stars: ✭ 151 (+18.9%)
CleanlabThe standard package for machine learning with noisy labels, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.
Stars: ✭ 2,526 (+1888.98%)
SnorkelA system for quickly generating training data with weak supervision
Stars: ✭ 4,953 (+3800%)
weak-supervision-for-NERFramework to learn Named Entity Recognition models without labelled data using weak supervision.
Stars: ✭ 114 (-10.24%)
WeSTClass[CIKM 2018] Weakly-Supervised Neural Text Classification
Stars: ✭ 67 (-47.24%)
WSCNNTDSaliency[BMVC17] Weakly Supervised Saliency Detection with A Category-Driven Map Generator
Stars: ✭ 19 (-85.04%)
RIBReducing Information Bottleneck for Weakly Supervised Semantic Segmentation (NeurIPS 2021)
Stars: ✭ 40 (-68.5%)
HiGitClassHiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories (ICDM'19)
Stars: ✭ 58 (-54.33%)