LGAPJul 14, 2025

Long-Tailed Data Classification by Increasing and Decreasing Neurons During Training

arXiv:2507.09940v12025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
Originality Highly original
AI Analysis

This addresses the challenge of reduced recognition accuracy for minority classes in real-world datasets with class imbalance, offering a biologically inspired solution.

The paper tackles the problem of class imbalance in deep learning by proposing a method that periodically adds and removes neurons during training to boost representational power for minority classes, demonstrating improved accuracy over fixed-size networks on three datasets and five models.

In conventional deep learning, the number of neurons typically remains fixed during training. However, insights from biology suggest that the human hippocampus undergoes continuous neuron generation and pruning of neurons over the course of learning, implying that a flexible allocation of capacity can contribute to enhance performance. Real-world datasets often exhibit class imbalance situations where certain classes have far fewer samples than others, leading to significantly reduce recognition accuracy for minority classes when relying on fixed size networks.To address the challenge, we propose a method that periodically adds and removes neurons during training, thereby boosting representational power for minority classes. By retaining critical features learned from majority classes while selectively increasing neurons for underrepresented classes, our approach dynamically adjusts capacity during training. Importantly, while the number of neurons changes throughout training, the final network size and structure remain unchanged, ensuring efficiency and compatibility with deployment.Furthermore, by experiments on three different datasets and five representative models, we demonstrate that the proposed method outperforms fixed size networks and shows even greater accuracy when combined with other imbalance-handling techniques. Our results underscore the effectiveness of dynamic, biologically inspired network designs in improving performance on class-imbalanced data.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes