Congratulations to Dr Aditya Dutt for successfully passing his PhD dissertation exam!
Dr Dutt’s research introduced the Contrastive MultiModal Alignment Network (COMMANet), a novel approach to shared manifold-based domain translation and fusion.
His work addressed the challenge of limited and imbalanced labeled datasets by leveraging contrastive learning with triplet networks to align multimodal data—such as SAR and optical images—in a shared latent space. Additionally, COMMANet enabled multimodal synthetic data generation, enhancing training in low-resource scenarios while maintaining consistent alignment across modalities.
This unified framework integrated both translation and classification tasks with a single model. We are excited to see more of your future achievements, Dr Dutt!