Kunal Sunil Kasodekar

Subodh Kamble, Kunal Sunil Kasodekar

Transformers models have become the backbone of the current state-of-the-art models in language, vision, and multimodal domains. These models, at their core, utilize multi-head self-attention to selectively aggregate context, generating dynamic contextual embeddings and modeling long-range dependencies for a clear contextual understanding. Lixi et al. \cite{zhou2022serving} proposed a method to use relational databases for deploying large-scale deep learning models and created an open-source implementation called NetsDB for the same. We build upon the previous work of these authors by creating an end-to-end implementation of the Encoder part of the transformer for model serving in NetsDB. Specifically, we construct a two-block encoder that includes Multi-Head Attention and its accompanying self-attention mechanism, Layer-Norm, Dropout, FeedForward Layers, and the necessary residual connections. We load out weights from our model for distributed processing, deployment, and efficient inferencing. To prove the efficacy of our implementation, we conduct a comprehensive performance analysis by comparing it with existing implementations in PyTorch, Tensorflow, Flax, and MxNet across key metrics such as inference time and model size.

Kunal Sunil Kasodekar

HiRISE (High-Resolution Imaging Science Experiment) is a camera onboard the Mars Reconnaissance orbiter responsible for photographing vast areas of the Martian surface in unprecedented detail. It can capture millions of incredible closeup images in minutes. However, Mars suffers from frequent regional and local dust storms hampering this data-collection process, and pipeline, resulting in loss of effort and crucial flight time. Removing these images manually requires a large amount of manpower. I filter out these images obstructed by atmospheric dust automatically by using a Dust Image Classifier fine-tuned on Resnet-50 with an accuracy of 94.05%. To further facilitate the seamless filtering of Images I design a prediction pipeline that classifies and stores these dusty patches. I also denoise partially obstructed images using an Auto Encoder-based denoiser and Pix2Pix GAN with 0.75 and 0.99 SSIM Index respectively.

Kunal Sunil Kasodekar

I explored adapting Stable Diffusion v1.5 for generating domain-specific satellite and aerial images in remote sensing. Recognizing the limitations of existing models like Midjourney and Stable Diffusion, trained primarily on natural RGB images and lacking context for remote sensing, I used the RSICD dataset to train a Stable Diffusion model with a loss of 0.2. I incorporated descriptive captions from the dataset for text-conditioning. Additionally, I created a synthetic dataset for a Land Use Land Classification (LULC) task, employing prompting techniques with RAG and ChatGPT and fine-tuning a specialized remote sensing LLM. However, I faced challenges with prompt quality and model performance. I trained a classification model (ResNet18) on the synthetic dataset achieving 49.48% test accuracy in TorchGeo to create a baseline. Quantitative evaluation through FID scores and qualitative feedback from domain experts assessed the realism and quality of the generated images and dataset. Despite extensive fine-tuning and dataset iterations, results indicated subpar image quality and realism, as indicated by high FID scores and domain-expert evaluation. These findings call attention to the potential of diffusion models in remote sensing while highlighting significant challenges related to insufficient pretraining data and computational resources.