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
논문
이 태스크와 하위 분야의 관련 논문입니다. 실제 성능 비교는 평가 결과에서 확인하세요.
PreMix: Addressing Label Scarcity in Whole Slide Image Classification with Pre-trained Multiple Instance Learning Aggregators
Active Learning for Neural PDE Solvers
A Cross-Domain Benchmark for Active Learning
dopanim: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
On the Pros and Cons of Active Learning for Moral Preference Elicitation
Learn from the Learnt: Source-Free Active Domain Adaptation via Contrastive Sampling and Visual Persistence
Amortized Active Learning for Nonparametric Functions
A Novel Two-Step Fine-Tuning Pipeline for Cold-Start Active Learning in Text Classification Tasks
MILAN: Milli-Annotations for Lidar Semantic Segmentation
Exploring and Addressing Reward Confusion in Offline Preference Learning
Self-driving lab discovers principles for steering spontaneous emission
Enhancing Retinal Disease Classification from OCTA Images via Active Learning Techniques
Downstream-Pretext Domain Knowledge Traceback for Active Learning
Enhancing Graph Neural Networks with Limited Labeled Data by Actively Distilling Knowledge from Large Language Models
The Future of Data Science Education
Generalized Coverage for More Robust Low-Budget Active Learning
On Machine Learning Approaches for Protein-Ligand Binding Affinity Prediction
Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
Learning Weighted Finite Automata over the Max-Plus Semiring and its Termination
Feasibility Study on Active Learning of Smart Surrogates for Scientific Simulations
Automated Neural Patent Landscaping in the Small Data Regime
Dataset Quantization with Active Learning based Adaptive Sampling
Active Label Refinement for Robust Training of Imbalanced Medical Image Classification Tasks in the Presence of High Label Noise
Pseudo-triplet Guided Few-shot Composed Image Retrieval
VideoCoT: A Video Chain-of-Thought Dataset with Active Annotation Tool
Leveraging Data Mining, Active Learning, and Domain Adaptation in a Multi-Stage, Machine Learning-Driven Approach for the Efficient Discovery of Advanced Acidic Oxygen Evolution Electrocatalysts
Markerless Multi-view 3D Human Pose Estimation: a survey
Automated Progressive Red Teaming
Scoping Review of Active Learning Strategies and their Evaluation Environments for Entity Recognition Tasks
Probing Perfection: The Relentless Art of Meddling for Pulmonary Airway Segmentation from HRCT via a Human-AI Collaboration Based Active Learning Method
Cost-Effective Proxy Reward Model Construction with On-Policy and Active Learning
CALICO: Confident Active Learning with Integrated Calibration
DCoM: Active Learning for All Learners
Physics-informed active learning with simultaneous weak-form latent space dynamics identification
Assistive Image Annotation Systems with Deep Learning and Natural Language Capabilities: A Review
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.