Many-MobileNet: Multi-Model Augmentation for Robust Retinal Disease Classification
This work addresses retinal disease classification, which is important for medical diagnosis, but it appears incremental as it builds on existing lightweight CNN and fusion techniques.
The paper tackled the problem of retinal disease classification by proposing Many-MobileNet, a model fusion strategy that uses multiple lightweight CNNs with varied data augmentations to address overfitting and limited data variability, achieving robust generalization in data-scarce domains while balancing computational efficiency.
In this work, we propose Many-MobileNet, an efficient model fusion strategy for retinal disease classification using lightweight CNN architecture. Our method addresses key challenges such as overfitting and limited dataset variability by training multiple models with distinct data augmentation strategies and different model complexities. Through this fusion technique, we achieved robust generalization in data-scarce domains while balancing computational efficiency with feature extraction capabilities.