https://github.com/humanlab/rare-class-AL
공식 코드Transfer and Active Learning for Dissonance Detection: Addressing the Rare-Class Challenge
Papers with Code 아카이브
Active Learning
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 1
- 보존된 평가 기록
- 7
Active Learning is a paradigm in supervised machine learning which uses fewer training examples to achieve better optimization by iteratively training a predictor, and using the predictor in each iteration to choose the training examples which will increase its chances of finding better configurations and at the same time improving the accuracy of the prediction model
Source: Polystore++: Accelerated Polystore System for Heterogeneous Workloads
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/hunto/actgen
공식 코드https://github.com/huyvvo/bib
공식 코드Active Learning Strategies for Weakly-supervised Object Detection
https://github.com/hyintell/al-dst
공식 코드https://github.com/hyperconnect/TiDAL
공식 코드https://github.com/hzykent/lidal
공식 코드LiDAL: Inter-frame Uncertainty Based Active Learning for 3D LiDAR Semantic Segmentation
https://github.com/i-pi/i-pi
공식 코드https://github.com/ia-gu/benchmarking-of-query-strategies-towards-future-deep-active-learning
공식 코드Benchmarking of Query Strategies: Towards Future Deep Active Learning
https://github.com/ibm/atari-active-learning
공식 코드Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari
https://github.com/ibpa/semiautomatedfoodkbc
공식 코드Semi-Automated Construction of Food Composition Knowledge Base
https://github.com/ichbill/DQAS
공식 코드Dataset Quantization with Active Learning based Adaptive Sampling
https://github.com/idejie/KAD
공식 코드Active Object Detection with Knowledge Aggregation and Distillation from Large Models
https://github.com/ielab/goldilocks-reproduce
공식 코드A Reproducibility Study of Goldilocks: Just-Right Tuning of BERT for TAR
https://github.com/ies-research/multi-annotator-machine-learning
공식 코드dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
https://github.com/imatge-upc/medical-2017-nipsw
공식 코드https://github.com/iminthemiddle/vatl4pose-wacv2024
공식 코드Active Transfer Learning for Efficient Video-Specific Human Pose Estimation
https://github.com/iml-dkfz/realistic-al
공식 코드https://github.com/iml-dkfz/values
공식 코드ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
https://github.com/immuno121/als4gan
공식 코드Active Learning for Improved Semi-Supervised Semantic Segmentation in Satellite Images
https://github.com/industryessentials/ymir
공식 코드YMIR: A Rapid Data-centric Development Platform for Vision Applications
https://github.com/iosband/ts_tutorial
공식 코드https://github.com/ipcng00/ldm-s
공식 코드Querying Easily Flip-flopped Samples for Deep Active Learning
https://github.com/ipeis/HH-VAEM
공식 코드Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo
https://github.com/isayev/ASE_ANI
공식 코드https://github.com/isayev/COMP6
공식 코드https://github.com/ivadomed/model-spinal-rootlets
공식 코드https://github.com/jacob-thrasher/AL-OCTA
공식 코드Enhancing Retinal Disease Classification from OCTA Images via Active Learning Techniques
https://github.com/jacobzhaoziyuan/DSAL
공식 코드https://github.com/jacobzhaoziyuan/SAAL
공식 코드Self-supervised Assisted Active Learning for Skin Lesion Segmentation
https://github.com/jaeohwoo/balancedentropy
공식 코드Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle
https://github.com/janelia-flyem/gala
공식 코드Machine learning of hierarchical clustering to segment 2D and 3D images
https://github.com/jasonkim8652/al_breakdown
공식 코드Understanding active learning of molecular docking and its applications
https://github.com/javadzb/class-balanced-al
공식 코드https://github.com/jdkuhnke/hic
공식 코드Image-based Detection of Surface Defects in Concrete during Construction
https://github.com/jellychen7/alemo
공식 코드Machine Learning-Accelerated Multi-Objective Design of Fractured Geothermal Systems
https://github.com/jgonsior/DS22-ImitAL
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.