In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a significant impact on learning performance.

The gap

Consensus across the literature

Supporting evidence — 5 representative gaps

• Evaluating the impact of preprocessing on CNN architectures: comparative analysis of a novel proposed model EyeDiagNet and existing models for eye disease detection (2026) · doi

  While data augmentation was applied to enhance model generalization, future studies could explore additional strategies such as focal loss or synthetic data generation to further strengthen robustness, particularly when extend- ing to datasets that may contain imbalances or rare disease categories.

  Keywords: augmentation applied enhance model generalization future explore additional strategies focal loss synthetic generation further strengthen
• Synthesis of a Small Fingerprint Database through a Deep Generative Model for Indoor Localisation (2023) · doi

  In deep learning (DL), the deep generative model is helpful for data augmentation objectives to tackle the lack of datasets that have a significant impact on learning performance.

  Keywords: deep learning generative model helpful augmentation objectives tackle lack datasets significant impact performance
• Collective Intelligence: Harnessing Multiple Models to Enhance Brain Tumor Detection and Classification Utilizing Deep Learning Techniques (2026) · doi

  Future research should focus on enhancing the model’s generalization by collecting more representative data, applying more sophisticated data augmentation techniques, and incorporating additional data types.

  Keywords: future focus enhancing model generalization collecting representative applying sophisticated augmentation techniques incorporating additional types
• Rice Maturity Level Segmentation in Paddy Fields Based on UAV Aerial Imagery Using the YOLOv8 Algorithm (2026) · doi

  Future research should consider expanding the dataset, incorporating additional envi- ronmental variations, and evaluating more advanced augmentation strategies to improve model robustness.

  Keywords: future consider expanding dataset incorporating additional envi ronmental variations evaluating advanced augmentation strategies improve model
• LLM-Based Visual Explanation Evaluation Framework for Assessing the Explainability of Facial Skin Disease Classification Models (2026)

  While previous studies have primarily focused on improving classification performance through data augmentation techniques, relatively few studies have systematically examined whether model explanations are grounded in clinically relevant lesion regions.

  Keywords: previous primarily focused improving classification performance augmentation techniques relatively systematically examined whether model explanations grounded