LGAICLCVMLJul 17, 2018

Cavity Filling: Pseudo-Feature Generation for Multi-Class Imbalanced Data Problems in Deep Learning

arXiv:1807.06538v63 citations
Originality Synthesis-oriented
AI Analysis

This addresses data imbalance issues in deep learning for real-world scenarios, but it appears incremental as it builds on existing augmentation techniques.

The paper tackles the problem of multi-class imbalanced data in deep learning by generating pseudo-features from feature maps to augment minor-class data, resulting in improved capabilities for real-world applications, though no concrete numbers are provided.

Herein, we generate pseudo-features based on the multivariate probability distributions obtained from the feature maps in layers of trained deep neural networks. Further, we augment the minor-class data based on these generated pseudo-features to overcome the imbalanced data problems. The proposed method, i.e., cavity filling, improves the deep learning capabilities in several problems because all the real-world data are observed to be imbalanced.

Foundations

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

Your Notes