Balanced Classification

Balanced classification aims to improve the performance of machine learning models on datasets with uneven class distributions, a common problem hindering accurate predictions, especially in applications like medical imaging and object detection. Current research focuses on developing novel loss functions and model architectures (e.g., vision transformers, MaxSAT-based rule learners) that address class imbalance by either re-weighting samples, synthesizing data for under-represented classes, or modifying model training procedures to better separate classes in feature space. These advancements are crucial for ensuring fair and reliable predictions across all classes, leading to more robust and equitable applications in various domains.

Papers

July 11, 2024

Adaptive Parametric Activation
Konstantinos Panagiotis Alexandridis, Jiankang Deng, Anh Nguyen, Shan Luo
Activation Function Balanced Classification Adaptive Activation

July 1, 2024

Task-oriented Over-the-air Computation for Edge-device Co-inference with Balanced Classification Accuracy
Xiang Jiao, Dingzhu Wen, Guangxu Zhu, Wei Jiang, Wu Luo, Yuanming Shi
Inference Task Inference Performance Balanced Classification Device Edge Co Inference

March 25, 2024

An Incremental MaxSAT-based Model to Learn Interpretable and Balanced Classification Rules
Antônio Carlos Souza Ferreira Júnior, Thiago Alves Rocha
Machine Learning Inherent Interpretability Interpretable Model Interpretable Way MaxSAT Solver Classification Rule Balanced Classification

October 16, 2023

Orthogonal Uncertainty Representation of Data Manifold for Robust Long-Tailed Learning
Yanbiao Ma, Licheng Jiao, Fang Liu, Shuyuan Yang, Xu Liu, Lingling Li
Long Tailed Long Tailed Learning Long Tail Long Tailed Distribution Data Manifold Uncertainty Representation Balanced Classification

August 16, 2023

SkinDistilViT: Lightweight Vision Transformer for Skin Lesion Classification
Vlad-Constantin Lungu-Stan, Dumitru-Clementin Cercel, Florin Pop
Vision Transformer Knowledge Distillation Skin Lesion Skin Cancer Balanced Classification Melanoma Diagnosis

August 4, 2023

Balanced Classification: A Unified Framework for Long-Tailed Object Detection
Tianhao Qi, Hongtao Xie, Pandeng Li, Jiannan Ge, Yongdong Zhang
Unified Framework Foreground Object Long Tailed Object Detection Balanced Classification

March 21, 2023

ViC-MAE: Self-Supervised Representation Learning from Images and Video with Contrastive Masked Autoencoders
Jefferson Hernandez, Ruben Villegas, Vicente Ordonez
Contrastive Learning Visual Representation Source Video Self Supervised Representation Learning Masked Autoencoders Video Benchmark Contrastive Masked Balanced Classification

October 21, 2022

Imbalanced Classification in Medical Imaging via Regrouping
Le Peng, Yash Travadi, Rui Zhang, Ying Cui, Ju Sun
Medical Imaging Medical Image Classification Classification Performance Imbalanced Classification Balanced Classification Balanced Data

May 24, 2022

Deep Reinforcement Learning for Multi-class Imbalanced Training
Jenny Yang, Rasheed El-Bouri, Odhran O'Donoghue, Alexander S. Lachapelle, Andrew A. S. Soltan, David A. Clifton
Reinforcement Learning Deep Reinforcement Learning Imbalanced Learning Double Deep Q Learning Class Imbalanced Learning Balanced Classification

January 22, 2022

Good Classification Measures and How to Find Them
Martijn Gösgens, Anton Zhiyanov, Alexey Tikhonov, Liudmila Prokhorenkova
Performance Metric Classification Metric Balanced Classification F Measure