paper-with-me

Papers

DeepAL: Deep Active Learning in Python

2021-11-30 · Kuan-Hao Huang

We present DeepAL, a Python library that implements several common strategies for active learning, with a particular emphasis on deep active learning. DeepAL provides a simple and unified framework based on PyTorch that allows users to easily load custom datasets, build custom data handlers, and design custom strategies without much modification of codes. DeepAL is open-source on Github and welcome any contribution.

📄 PDF Abstract BibTeX arXiv:2111.15258

Code (2)

ej0cl6/deep-active-learning 공식 구현 pytorch
debabrota-basu/marich pytorch

Tasks

Active Learning

Similar Papers 제목 키워드 기반

DeepAlign: Alignment-based Process Anomaly Correction using Recurrent Neural Networks

2019-11-29 · Timo Nolle, Alexander Seeliger, Nils Thoma, Max Mühlhäuser

In this paper, we propose DeepAlign, a novel approach to multi-perspective process anomaly correction, based on recurrent neural networks and bidirectional beam search. At the core of the DeepAlign algorithm are two recu…

DeepAlignment: Unsupervised Ontology Matching with Refined Word Vectors

2018-06-01 · NAACL 2018 6 · Prodromos Kolyvakis, Alex Kalousis, ros, Dimitris Kiritsis

Ontologies compartmentalize types and relations in a target domain and provide the semantic backbone needed for a plethora of practical applications. Very often different ontologies are developed independently for the sa…

Entity AlignmentFeature EngineeringOntology MatchingRepresentation Learning

DeepAltTrip: Top-k Alternative Itineraries for Trip Recommendation

2021-09-08 · Syed Md. Mukit Rashid, Mohammed Eunus Ali, Muhammad Aamir Cheema

Trip itinerary recommendation finds an ordered sequence of Points-of-Interest (POIs) from a large number of candidate POIs in a city. In this paper, we propose a deep learning-based framework, called DeepAltTrip, that le…

High Accuracy and Cost-Saving Active Learning 3D WD-UNet for Airway Segmentation

2023-10-09 · Shiyi Wang, Yang Nan, Simon Walsh, Guang Yang

We propose a novel Deep Active Learning (DeepAL) model-3D Wasserstein Discriminative UNet (WD-UNet) for reducing the annotation effort of medical 3D Computed Tomography (CT) segmentation. The proposed WD-UNet learns in a…

Active LearningComputed Tomography (CT)Segmentation

A Comparative Survey of Deep Active Learning

2022-03-25 · Xueying Zhan, Qingzhong Wang, Kuan-Hao Huang, Haoyi Xiong 외

While deep learning (DL) is data-hungry and usually relies on extensive labeled data to deliver good performance, Active Learning (AL) reduces labeling costs by selecting a small proportion of samples from unlabeled data…

Active LearningSurvey