TasksSotADatasetsPapersMethodsSubmitAbout
Papers With Code 2

A community resource for machine learning research: papers, code, benchmarks, and state-of-the-art results.

Explore

Notable BenchmarksAll SotADatasetsPapersMethods

Community

Submit ResultsAbout

Data sourced from the PWC Archive (CC-BY-SA 4.0). Built by the community, for the community.

Papers/Influence-Balanced Loss for Imbalanced Visual Classification

Influence-Balanced Loss for Imbalanced Visual Classification

Seulki Park, Jongin Lim, Younghan Jeon, Jin Young Choi

2021-10-06ICCV 2021 10Meta-LearningLong-tail LearningClassification
PaperPDFCode(official)

Abstract

In this paper, we propose a balancing training method to address problems in imbalanced data learning. To this end, we derive a new loss used in the balancing training phase that alleviates the influence of samples that cause an overfitted decision boundary. The proposed loss efficiently improves the performance of any type of imbalance learning methods. In experiments on multiple benchmark data sets, we demonstrate the validity of our method and reveal that the proposed loss outperforms the state-of-the-art cost-sensitive loss methods. Furthermore, since our loss is not restricted to a specific task, model, or training method, it can be easily used in combination with other recent re-sampling, meta-learning, and cost-sensitive learning methods for class-imbalance problems.

Results

TaskDatasetMetricValueModel
Image ClassificationCIFAR-10-LT (ρ=10)Error Rate12.93IBLLoss
Image ClassificationCIFAR-100-LT (ρ=100)Error Rate61.52IBLLoss
Few-Shot Image ClassificationCIFAR-10-LT (ρ=10)Error Rate12.93IBLLoss
Few-Shot Image ClassificationCIFAR-100-LT (ρ=100)Error Rate61.52IBLLoss
Generalized Few-Shot ClassificationCIFAR-10-LT (ρ=10)Error Rate12.93IBLLoss
Generalized Few-Shot ClassificationCIFAR-100-LT (ρ=100)Error Rate61.52IBLLoss
Long-tail LearningCIFAR-10-LT (ρ=10)Error Rate12.93IBLLoss
Long-tail LearningCIFAR-100-LT (ρ=100)Error Rate61.52IBLLoss
Generalized Few-Shot LearningCIFAR-10-LT (ρ=10)Error Rate12.93IBLLoss
Generalized Few-Shot LearningCIFAR-100-LT (ρ=100)Error Rate61.52IBLLoss

Related Papers

Adversarial attacks to image classification systems using evolutionary algorithms2025-07-17Are encoders able to learn landmarkers for warm-starting of Hyperparameter Optimization?2025-07-16Imbalanced Regression Pipeline Recommendation2025-07-16CLID-MU: Cross-Layer Information Divergence Based Meta Update Strategy for Learning with Noisy Labels2025-07-16Efficient Calisthenics Skills Classification through Foreground Instance Selection and Depth Estimation2025-07-16Safeguarding Federated Learning-based Road Condition Classification2025-07-16Mixture of Experts in Large Language Models2025-07-15Iceberg: Enhancing HLS Modeling with Synthetic Data2025-07-14