Search Results for author:
Found 6 papers, 1 papers with code
PHEW: Paths with Higher Edge-Weights give ''winning tickets'' without training data
Then, we show that Paths with Higher Edge-Weights (PHEW) at initialization have higher loss gradient magnitude, resulting in more efficient training.
PHEW: Constructing Sparse Networks that Learn Fast and Generalize Well without Training Data
Our work is based on a recently proposed decomposition of the Neural Tangent Kernel (NTK) that has decoupled the dynamics of the training process into a data-dependent component and an architecture-dependent kernel - the latter referred to as Path Kernel.
A Multi-task Framework for Skin Lesion Detection and Segmentation
This underlines the need for an accurate and automatic approach to skin lesion segmentation.
Siamese LSTM based Fiber Structural Similarity Network (FS2Net) for Rotation Invariant Brain Tractography Segmentation
In this paper, we propose a novel deep learning architecture combining stacked Bi-directional LSTM and LSTMs with the Siamese network architecture for segmentation of brain fibers, obtained from tractography data, into anatomically meaningful clusters.
BrainSegNet : A Segmentation Network for Human Brain Fiber Tractography Data into Anatomically Meaningful Clusters
The segregation of brain fiber tractography data into distinct and anatomically meaningful clusters can help to comprehend the complex brain structure and early investigation and management of various neural disorders.
UBSegNet: Unified Biometric Region of Interest Segmentation Network
In this paper, we have proposed a novel end-to-end, Unified Biometric ROI Segmentation Network (UBSegNet), for extracting region of interest from five different biometric traits viz.
