activity
20152019
most citedMultitask Learning of Temporal Connectionism in Convolutional Networks using a Joint Distribution Loss Function to Simultaneously Identify Tools and Phase in Surgical Videos

13 citations · 21 across the 6 of their papers we have counts for

collaborators

8 papers

cs.CV20192 cited

Adversarially Trained Deep Neural Semantic Hashing Scheme for Subjective Search in Fashion Inventory

Saket Singh, Debdoot Sheet, Mithun Dasgupta

The simple approach of retrieving a closest match of a query image from one in the gallery, compares an image pair using sum of absolute difference in pixel or feature space. The p…

cs.LG20191 cited

Unit Impulse Response as an Explainer of Redundancy in a Deep Convolutional Neural Network

Rachana Sathish, Debdoot Sheet

Convolutional neural networks (CNN) are generally designed with a heuristic initialization of network architecture and trained for a certain task. This often leads to overparametri…

eess.IV201913 cited

Multitask Learning of Temporal Connectionism in Convolutional Networks using a Joint Distribution Loss Function to Simultaneously Identify Tools and Phase in Surgical Videos

Shanka Subhra Mondal, Rachana Sathish, Debdoot Sheet

Surgical workflow analysis is of importance for understanding onset and persistence of surgical phases and individual tool usage across surgery and in each phase. It is beneficial…

cs.CV2018

Simulating Patho-realistic Ultrasound Images using Deep Generative Networks with Adversarial Learning

Francis Tom, Debdoot Sheet

Ultrasound imaging makes use of backscattering of waves during their interaction with scatterers present in biological tissues. Simulation of synthetic ultrasound images is a chall…

cs.CV2017

Error Corrective Boosting for Learning Fully Convolutional Networks with Limited Data

Abhijit Guha Roy, Sailesh Conjeti, Debdoot Sheet +3

Training deep fully convolutional neural networks (F-CNNs) for semantic image segmentation requires access to abundant labeled data. While large datasets of unlabeled image data ar…

cs.CV2016

DASA: Domain Adaptation in Stacked Autoencoders using Systematic Dropout

Abhijit Guha Roy, Debdoot Sheet

Domain adaptation deals with adapting behaviour of machine learning based systems trained using samples in source domain to their deployment in target domain where the statistics o…