• Publications
  • Influence
ESPNet: Efficient Spatial Pyramid of Dilated Convolutions for Semantic Segmentation
TLDR
A fast and efficient convolutional neural network, ESPNet, for semantic segmentation of high resolution images under resource constraints, which outperforms all the current efficient CNN networks such as MobileNet, ShuffleNet, and ENet on both standard metrics and the newly introduced performance metrics that measure efficiency on edge devices.
ESPNetv2: A Light-Weight, Power Efficient, and General Purpose Convolutional Neural Network
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise
Y-Net: Joint Segmentation and Classification for Diagnosis of Breast Biopsy Images
TLDR
Y-Net extends and generalizes U-Net by adding a parallel branch for discriminative map generation and by supporting convolutional block modularity, which allows the user to adjust network efficiency without altering the network topology.
3D-ESPNet with Pyramidal Refinement for Volumetric Brain Tumor Image Segmentation
TLDR
This paper extends ESPNet, a fast and efficient network designed for vanilla 2D semantic segmentation, to challenging 3D data in the medical imaging domain, and achieves respectable brain tumor segmentation results, while learning only 3.8 million parameters.
A Study of DWT and SVD Based Watermarking Algorithms for Patient Privacy in Medical Images
TLDR
The quality of watermarked images obtained after embedding the watermarks using both objective (PSNR) as well as subjective (opinions from physicians, a radiologist and a medical physicist) methods are found to have not resulted in loss of medical information.
DiCENet: Dimension-wise Convolutions for Efficient Networks
TLDR
When DiCE units are stacked to build the DiCENet model, they observe significant improvements over state-of-the-art models across various computer vision tasks including image classification, object detection, and semantic segmentation.
ESPNetv 2 : A Light-weight , Power Efficient , and General Purpose Convolutional Neural Network
We introduce a light-weight, power efficient, and general purpose convolutional neural network, ESPNetv2, for modeling visual and sequential data. Our network uses group point-wise and depth-wise
Automated Diagnosis of Breast Cancer and Pre-invasive Lesions on Digital Whole Slide Images
TLDR
A dataset of 240 digital slides that are interpreted and diagnosed by an expert panel is used to develop and evaluate image features for diagnostic classification of breast biopsy whole slides to four categories: benign, atypia, ductal carcinoma in-situ and invasive carcinoma.
Identifying Most Walkable Direction for Navigation in an Outdoor Environment
TLDR
This work constructs a new annotated navigation dataset collected using a hand-held mobile camera in an unconstrained outdoor environment, which includes challenging settings such as highly dynamic scenes, occlusion between objects, and distortions.
3D content fingerprinting
TLDR
Experimental results show that the proposed two pass method for content fingerprinting of Depth-Image-Based-Rendering (DIBR) 3D videos is as robust as keypoint based local fingerprinting method.
...
1
2
3
...