2 citations · 2 across the 6 of their papers we have counts for
8 papers
A PyTorch Library for Hyperspectral Image Models: Technical Report
Tanishq Rachamalla, Aryan Das, Srishti Kaushik +1
Hyperspectral remote sensing has advanced across diverse deep learning paradigms, including spectral spatial CNNs, Vision Transformers, Mamba, graph neural networks, Kolmogorov Arn…
OptiModNet: A UNet-Transformer Hybrid with Grouped-Query and Channel Attention for Optic Disc and Cup Segmentation
Soumili Ghosh, Debapriya Roy, Aryan Das +1
Precise segmentation of the optic disc and cup is critical for the early detection and diagnosis of glaucoma. However, achieving consistently high performance across datasets while…
Prototype-Rectified Iterative Self-supervised Manifold Denoising under Severe Acoustic Shift
Ashish Anand Shukla, Rini Smita Thakur, Aryan Das +1
Audio-Text Foundation Models (ATMs) fail catastrophically under severe acoustic noise, yet existing adaptation strategies either rely on gradient-based Test-Time Adaptation (TTA),…
UNITY: Attention Flow Networks for Adaptive Conditioning in Diffusion
Aryan Das, Koushik Biswas, Moloud Abdar +1
We introduce UNITY, a Universal-to-Specialized adapter for efficient and scalable composite conditioning in diffusion based image generation. Unlike prior methods that train separa…
Efficient Text-Guided Convolutional Adapter for the Diffusion Model
Aryan Das, Koushik Biswas, Swalpa Kumar Roy +2
We introduce the Nexus Adapters, novel text-guided efficient adapters to the diffusion-based framework for the Structure Preserving Conditional Generation (SPCG). Recently, structu…
Uncertainty-Aware Vision-Language Segmentation for Medical Imaging
Aryan Das, Tanishq Rachamalla, Koushik Biswas +2
We introduce a novel uncertainty-aware multimodal segmentation framework that leverages both radiological images and associated clinical text for precise medical diagnosis. We prop…
HyperCap: Hyperspectral Land Cover Captioning Dataset for Vision Language Models
Aryan Das, Tanishq Rachamalla, Pravendra Singh +5
We introduce HyperCap, the first large-scale hyperspectral captioning dataset designed to enhance model performance and effectiveness in remote sensing applications. Unlike traditi…
Leveraging Task-Specific Knowledge from LLM for Semi-Supervised 3D Medical Image Segmentation
Suruchi Kumari, Aryan Das, Swalpa Kumar Roy +2
Traditional supervised 3D medical image segmentation models need voxel-level annotations, which require huge human effort, time, and cost. Semi-supervised learning (SSL) addresses…