3 papers
cs.CV2026
From Bands to Depth: Understanding Bathymetry Decisions on Sentinel-2
Satyaki Roy Chowdhury, Aswathnarayan Radhakrishnan, Hsiao Jou Hsu +2
Deploying Sentinel-2 satellite derived bathymetry (SDB) robustly across sites remains challenging. We analyze a Swin-Transformer based U-Net model (Swin-BathyUNet) to understand ho…
cs.CV2026
Variance-Penalized MC-Dropout as a Learned Smoothing Prior for Brain Tumour Segmentation
Satyaki Roy Chowdhury, Golrokh Mirzaei
Brain tumor segmentation is essential for diagnosis and treatment planning, yet many CNN and U-Net based approaches produce noisy boundaries in regions of tumor infiltration. We in…
eess.IV2025
Hybridization of Attention UNet with Repeated Atrous Spatial Pyramid Pooling for Improved Brain Tumour Segmentation
Satyaki Roy Chowdhury, Golrokh Mirzaei
Brain tumors are highly heterogeneous in terms of their spatial and scaling characteristics, making tumor segmentation in medical images a difficult task that might result in wrong…