Baseline Model

Baseline models serve as crucial points of comparison in evaluating the performance of new machine learning models across diverse fields, from healthcare and natural language processing to weather forecasting and image analysis. Current research emphasizes the need for stronger, more appropriate baselines, often focusing on established statistical methods or simpler architectures like linear models and Markov models, to accurately gauge the true advancements offered by novel approaches. The development and use of robust baselines are essential for ensuring the reproducibility and reliability of research findings, ultimately improving the validity and impact of machine learning applications in various domains.

Papers

January 9, 2023

The Optimal Input-Independent Baseline for Binary Classification: The Dutch Draw
Joris Pries, Etienne van de Bijl, Jan Klein, Sandjai Bhulai, Rob van der Mei
Binary Classification Binary Classifier Baseline Model Baseline Method Independent Classifier Optimal Baseline

December 21, 2022

Advanced Baseline for 3D Human Pose Estimation: A Two-Stage Approach
Zichen Gui, Jungang Luo
Computer Vision Human Pose Estimation 3D Human 3D Human Pose Estimation Baseline Model Two Stage Approach Lifting Task

December 5, 2022

Solving the Weather4cast Challenge via Visual Transformers for 3D Images
Yury Belousov, Sergey Polezhaev, Brian Pulfer
Vision Transformer Computer Vision Weather Forecasting Transformer Based Architecture Baseline Model 3d Image Weather4cast Challenge

August 24, 2022

Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer
Fengji Zhang, Jin Liu, Yao Wan, Xiao Yu, Xiao Liu, Jacky Keung
Automatic Evaluation Code Snippet Baseline Model Stack Overflow Programming Community

July 7, 2022

HierarchicalForecast: A Reference Framework for Hierarchical Forecasting in Python
Kin G. Olivares, Federico Garza, David Luo, Cristian Challú, Max Mergenthaler, Souhaib Ben Taieb, Shanika L. Wickramasuriya, Artur Dubrawski
Baseline Model Hierarchical Forecasting Reference Model Learning Based Forecasting Forecast Aggregation

July 3, 2022

ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes
Kenneth Ooi, Zhen-Ting Ong, Karn N. Watcharasupat, Bhan Lam, Joo Young Hong, Woon-Seng Gan
Large Scale Dataset Baseline Model Affective Response Soundscape Augmentation

July 1, 2022

A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos
Zhi Lin, Junhao Lin, Lei Zhu, Huazhu Fu, Jing Qin, Liansheng Wang
Baseline Model Ultrasound Video Breast Lesion Detection 2 Dimensional Ultrasound

June 8, 2022

Blind Face Restoration: Benchmark Datasets and a Baseline Model
Puyang Zhang, Kaihao Zhang, Wenhan Luo, Changsheng Li, Guoren Wang
Benchmark Datasets Blind Face Restoration Baseline Model

May 24, 2022

FreDo: Frequency Domain-based Long-Term Time Series Forecasting
Fan-Keng Sun, Duane S. Boning
Neural Network Model High Frequency Long Term Time Series Forecasting Long Term Forecasting Baseline Model

May 22, 2022

Offline Policy Comparison with Confidence: Benchmarks and Baselines
Anurag Koul, Mariano Phielipp, Alan Fern
New Benchmark Offline Reinforcement Learning Baseline Result High Confidence Comparative Evaluation Baseline Model Offline Policy Evaluation Sequential Decision Making Policy

May 2, 2022

WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline models
Sagar Garg, Stephan Rasp, Nils Thuerey
Benchmark Dataset Ensemble Forecast Medium Range Baseline Model

Baseline Model

Papers

The Optimal Input-Independent Baseline for Binary Classification: The Dutch Draw

Advanced Baseline for 3D Human Pose Estimation: A Two-Stage Approach

Solving the Weather4cast Challenge via Visual Transformers for 3D Images

Diverse Title Generation for Stack Overflow Posts with Multiple Sampling Enhanced Transformer

HierarchicalForecast: A Reference Framework for Hierarchical Forecasting in Python

ARAUS: A Large-Scale Dataset and Baseline Models of Affective Responses to Augmented Urban Soundscapes

A New Dataset and A Baseline Model for Breast Lesion Detection in Ultrasound Videos

Blind Face Restoration: Benchmark Datasets and a Baseline Model

FreDo: Frequency Domain-based Long-Term Time Series Forecasting

Offline Policy Comparison with Confidence: Benchmarks and Baselines

WeatherBench Probability: A benchmark dataset for probabilistic medium-range weather forecasting along with deep learning baseline models