12 citations · 40 across the 18 of their papers we have counts for
14 papers · 1 filter
Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images
Ardhendu Sekhar, Vasu Soni, Keshav Aske +3
Accurate survival prediction from histopathology whole-slide images (WSIs) remains challenging due to their gigapixel resolution, strong spatial heterogeneity, and complex survival…
Survival Modeling from Whole Slide Images via Patch-Level Graph Clustering and Mixture Density Experts
Ardhendu Sekhar, Vasu Soni, Keshav Aske +3
We propose a modular framework for predicting cancer specific survival directly from whole slide pathology images (WSIs). The framework consists of four key stages designed to capt…
FLD+: Data-efficient Evaluation Metric for Generative Models
Pranav Jeevan, Neeraj Nixon, Amit Sethi
We introduce a new metric to assess the quality of generated images that is more reliable, data-efficient, compute-efficient, and adaptable to new domains than the previous metrics…
Normalizing Flow-Based Metric for Image Generation
Pranav Jeevan, Neeraj Nixon, Amit Sethi
We propose two new evaluation metrics to assess realness of generated images based on normalizing flows: a simpler and efficient flow-based likelihood distance (FLD) and a more exa…
EDSNet: Efficient-DSNet for Video Summarization
Ashish Prasad, Pranav Jeevan, Amit Sethi
Current video summarization methods largely rely on transformer-based architectures, which, due to their quadratic complexity, require substantial computational resources. In this…
Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision
Pranav Jeevan, Amit Sethi
In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as featur…
Heterogeneous graphs model spatial relationships between biological entities for breast cancer diagnosis
Akhila Krishna K, Ravi Kant Gupta, Nikhil Cherian Kurian +2
The heterogeneity of breast cancer presents considerable challenges for its early detection, prognosis, and treatment selection. Convolutional neural networks often neglect the spa…
WaveMixSR: A Resource-efficient Neural Network for Image Super-resolution
Pranav Jeevan, Akella Srinidhi, Pasunuri Prathiba +1
Image super-resolution research recently been dominated by transformer models which need higher computational resources than CNNs due to the quadratic complexity of self-attention.…
WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting
Pranav Jeevan, Dharshan Sampath Kumar, Amit Sethi
Image inpainting, which refers to the synthesis of missing regions in an image, can help restore occluded or degraded areas and also serve as a precursor task for self-supervision.…
CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation
Chirag P, Mukta Wagle, Ravi Kant Gupta +2
We propose a new technique called CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation. Adversarial training is commonly used for lear…
WaveMix: A Resource-efficient Neural Network for Image Analysis
Pranav Jeevan, Kavitha Viswanathan, Anandu A S +1
We propose a novel neural architecture for computer vision -- WaveMix -- that is resource-efficient and yet generalizable and scalable. While using fewer trainable parameters, GPU…
WaveMix: Resource-efficient Token Mixing for Images
Pranav Jeevan, Amit Sethi
Although certain vision transformer (ViT) and CNN architectures generalize well on vision tasks, it is often impractical to use them on green, edge, or desktop computing due to the…
Convolutional Xformers for Vision
Pranav Jeevan, Amit sethi
Vision transformers (ViTs) have found only limited practical use in processing images, in spite of their state-of-the-art accuracy on certain benchmarks. The reason for their limit…
Vision Xformers: Efficient Attention for Image Classification
Pranav Jeevan, Amit Sethi
Although transformers have become the neural architectures of choice for natural language processing, they require orders of magnitude more training data, GPU memory, and computati…