83 Open source projects that are alternatives of or similar to weasel

Self-training with Weak Supervision (NAACL 2021)

Dataset for paper "Weak Supervision for Fake News Detection via Reinforcement Learning" published in AAAI'2020.

A 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.

WRENCH: Weak supeRvision bENCHmark

Library implementing state-of-the-art Concept-based and Disentanglement Learning methods for Explainable AI

Weakly supervised medical named entity classification

Implementation of experiments in paper "Learning from Rules Generalizing Labeled Exemplars" to appear in ICLR2020 (https://openreview.net/forum?id=SkeuexBtDr)

Framework to learn Named Entity Recognition models without labelled data using weak supervision.

PyTorch Implementation of SOTA SSL methods

PyTorch implementation of AAAI 2021 paper: A Hybrid Attention Mechanism for Weakly-Supervised Temporal Action Localization

(Machine) Learning to Do More with Less

A curated list of programmatic weak supervision papers and resources

Scribbles or Points-based weakly-supervised learning for medical image segmentation, a strong baseline, and tutorial for research and application.

SPEAR: Programmatically label and build training data quickly.

Clean minimal implementation of Free-Form Image Inpainting with Gated Convolutions in pytorch lightning. Inspired from pytorch implementation by @avalonstrel.

[CIKM 2018] Weakly-Supervised Neural Text Classification

A curated (most recent) list of resources for Learning with Noisy Labels

Automatic machine learning for tabular data. ⚡🔥⚡

A curated publication list on weakly-supervised temporal action localization

Official version of 'Weakly Supervised 3D object detection from Lidar Point Cloud'(ECCV2020)

A 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.

[TPAMI Special Issue on ICCV 2021 Best Papers, Oral] Just Ask: Learning to Answer Questions from Millions of Narrated Videos

Minimally Supervised Categorization of Text with Metadata (SIGIR'20)

Implementation for "3D human pose, shape and texture from low-resolution images and videos", TPAMI 2021

Codes for TS-CAM: Token Semantic Coupled Attention Map for Weakly Supervised Object Localization.

A curated list of papers, code and resources pertaining to weak-shot classification, detection, and segmentation.

Implement Question Generator with SOTA pre-trained Language Models (RoBERTa, BERT, GPT, BART, T5, etc.)

No description or website provided.

Source code of the KDD19 paper "Deep anomaly detection with deviation networks", weakly/partially supervised anomaly detection, few-shot anomaly detection

PyTorch Lightning + Hydra. A very user-friendly template for rapid and reproducible ML experimentation with best practices. ⚡🔥⚡

PyTorch implementation of a collections of scalable Video Transformer Benchmarks.

Implementation of Cluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification approach.

This repository focuses on training semantic segmentation models to predict the presence of floodwater for disaster prevention. Models were trained using SageMaker and Colab.

Code for ECCV 2020 paper (oral): Mining Cross-Image Semantics for Weakly Supervised Semantic Segmentation

Fast Differentiable Forest lib with the advantages of both decision trees and neural networks

Weakly supervised 3D classification of multi-disease chest CT scans using multi-resolution deep segmentation features via dual-stage CNN architecture (DenseVNet, 3D Residual U-Net).

Unofficial PyTorch Implementation for HifiFace (https://arxiv.org/abs/2106.09965)

[BMVC17] Weakly Supervised Saliency Detection with A Category-Driven Map Generator

Brain extraction in presence of abnormalities, using single and multiple MRI modalities

Reducing Information Bottleneck for Weakly Supervised Semantic Segmentation (NeurIPS 2021)

A deep learning model to age faces in the wild, currently runs at 60+ fps on GPUs

HiGitClass: Keyword-Driven Hierarchical Classification of GitHub Repositories (ICDM'19)

Weakly Supervised Dense Event Captioning in Videos, i.e. generating multiple sentence descriptions for a video in a weakly-supervised manner.

Generative Adversarial Learning Towards Fast Weakly Supervised Detection

Pythonic functions for creating and enhancing Hydra applications

Official Pytorch Implementation of 'Learning Action Completeness from Points for Weakly-supervised Temporal Action Localization' (ICCV-21 Oral)

Implementation of DeepMind's Deep Generative Model of Radar (DGMR) https://arxiv.org/abs/2104.00954

Weakly Supervised Segmentation by Tensorflow. Implements semantic segmentation in Simple Does It: Weakly Supervised Instance and Semantic Segmentation, by Khoreva et al. (CVPR 2017).

The Official PyTorch Implementation of DiscoBox.

Repository of Jupyter notebook tutorials for teaching the Deep Learning Course at the University of Amsterdam (MSc AI), Fall 2022/Spring 2022

Universal Weakly Supervised Segmentation by Pixel-to-Segment Contrastive Learning

Automatically labeling training data

Code for Paper Abstract Writing through Editing Mechanism

neural network based speaker embedder

[AAAI 2019] Weakly-Supervised Hierarchical Text Classification

🔎 Monitor deep learning model training and hardware usage from your mobile phone 📱

An 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.

The standard package for machine learning with noisy labels, finding mislabeled data, and uncertainty quantification. Works with most datasets and models.

The 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.

A system for quickly generating training data with weak supervision