Pranav Jeevan
YOU?
Author Swipe
View article: Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images
Spatially-Aware Mixture of Experts with Log-Logistic Survival Modeling for Whole-Slide Images Open
Accurate survival prediction from histopathology whole-slide images (WSIs) remains challenging due to their gigapixel resolution, strong spatial heterogeneity, and complex survival distributions. We introduce a comprehensive computational …
View article: Survival Modeling from Whole Slide Images via Patch-Level Graph Clustering and Mixture Density Experts
Survival Modeling from Whole Slide Images via Patch-Level Graph Clustering and Mixture Density Experts Open
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 capture prognostic and morphological heterogeneity. First, a Qu…
View article: WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency (Student Abstract)
WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency (Student Abstract) Open
Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spat…
View article: FLD+: Data-efficient Evaluation Metric for Generative Models
FLD+: Data-efficient Evaluation Metric for Generative Models Open
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, such as Fréchet Inception Distance (FID). The proposed me…
View article: Normalizing Flow-Based Metric for Image Generation
Normalizing Flow-Based Metric for Image Generation Open
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 exact dual-flow based likelihood distance (D-FLD). Because nor…
View article: EDSNet: Efficient-DSNet for Video Summarization
EDSNet: Efficient-DSNet for Video Summarization Open
Current video summarization methods largely rely on transformer-based architectures, which, due to their quadratic complexity, require substantial computational resources. In this work, we address these inefficiencies by enhancing the Dire…
View article: FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch
FLeNS: Federated Learning with Enhanced Nesterov-Newton Sketch Open
Federated learning faces a critical challenge in balancing communication efficiency with rapid convergence, especially for second-order methods. While Newton-type algorithms achieve linear convergence in communication rounds, transmitting …
View article: WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency
WaveMixSR-V2: Enhancing Super-resolution with Higher Efficiency Open
Recent advancements in single image super-resolution have been predominantly driven by token mixers and transformer architectures. WaveMixSR utilized the WaveMix architecture, employing a two-dimensional discrete wavelet transform for spat…
View article: Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision
Which Backbone to Use: A Resource-efficient Domain Specific Comparison for Computer Vision Open
In contemporary computer vision applications, particularly image classification, architectural backbones pre-trained on large datasets like ImageNet are commonly employed as feature extractors. Despite the widespread use of these pre-train…
View article: Advancing Gene Selection in Oncology: A Fusion of Deep Learning and Sparsity for Precision Gene Selection
Advancing Gene Selection in Oncology: A Fusion of Deep Learning and Sparsity for Precision Gene Selection Open
Gene selection plays a pivotal role in oncology research for improving outcome prediction accuracy and facilitating cost-effective genomic profiling for cancer patients. This paper introduces two gene selection strategies for deep learning…
View article: Heterogeneous graphs model spatial relationships between biological entities for breast cancer diagnosis
Heterogeneous graphs model spatial relationships between biological entities for breast cancer diagnosis Open
The heterogeneity of breast cancer presents considerable challenges for its early detection, prognosis, and treatment selection. Convolutional neural networks often neglect the spatial relationships within histopathological images, which c…
View article: WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting
WavePaint: Resource-efficient Token-mixer for Self-supervised Inpainting Open
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. The current state-of-the-art models for image inpainting a…
View article: CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation
CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation Open
We propose a new technique called CHATTY: Coupled Holistic Adversarial Transport Terms with Yield for Unsupervised Domain Adaptation. Adversarial training is commonly used for learning domain-invariant representations by reversing the grad…
View article: Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers
Magnification Invariant Medical Image Analysis: A Comparison of Convolutional Networks, Vision Transformers, and Token Mixers Open
Convolution Neural Networks (CNNs) are widely used in medical image analysis, but their performance degrade when the magnification of testing images differ from the training images. The inability of CNNs to generalize across magnification …
View article: WaveMix: A Resource-efficient Neural Network for Image Analysis
WaveMix: A Resource-efficient Neural Network for Image Analysis Open
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 RAM, and computations, WaveMix networks achieve comparable …
View article: WaveMix: Resource-efficient Token Mixing for Images
WaveMix: Resource-efficient Token Mixing for Images Open
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 their computational requirements for training and even testing…
View article: Convolutional Xformers for Vision
Convolutional Xformers for Vision Open
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 limited use include their need for larger training datasets and …