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.
Automated Gain Control Through Deep Reinforcement Learning for Downstream Radar Object Detection
RISAN: Robust Instance Specific Abstention Network
Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answering
Prioritized training on points that are learnable, worth learning, and not yet learned (workshop version)
Matching a Desired Causal State via Shift Interventions
SCOD: Active Object Detection for Embodied Agents using Sensory Commutativity of Action Sequences
Near-optimal inference in adaptive linear regression
Knowledge Modelling and Active Learning in Manufacturing
Multiple-criteria Based Active Learning with Fixed-size Determinantal Point Processes
Non-parametric Semi-Supervised Learning in Many-body Hilbert Space with Rescaled Logarithmic Fidelity
Active Learning of Abstract Plan Feasibility
SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarios
On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction
TableSense: Spreadsheet Table Detection with Convolutional Neural Networks
Multi-Domain Active Learning: Literature Review and Comparative Study
Active Learning with Multifidelity Modeling for Efficient Rare Event Simulation
TagRuler: Interactive Tool for Span-Level Data Programming by Demonstration
Distributional Gradient Matching for Learning Uncertain Neural Dynamics Models
Test Distribution-Aware Active Learning: A Principled Approach Against Distribution Shift and Outliers
MEAL: Manifold Embedding-based Active Learning
Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detection
Stochastic Batch Acquisition: A Simple Baseline for Deep Active Learning
A Practical & Unified Notation for Information-Theoretic Quantities in ML
Active Learning for Deep Neural Networks on Edge Devices
ArgFuse: A Weakly-Supervised Framework for Document-Level Event Argument Aggregation
Corruption Robust Active Learning
Active and Dynamic Beam Tracking UnderStochastic Mobility
Phrase-level Active Learning for Neural Machine Translation
Quality-Aware Memory Network for Interactive Volumetric Image Segmentation
On Minimizing Cost in Legal Document Review Workflows
Heuristic Stopping Rules For Technology-Assisted Review
Gone Fishing: Neural Active Learning with Fisher Embeddings
An Information Retrieval Approach to Building Datasets for Hate Speech Detection
A Survey on Semi-Supervised Learning for Delayed Partially Labelled Data Streams
Effective Evaluation of Deep Active Learning on Image Classification Tasks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.