no code implementations • 23 Apr 2021 • Bodhisatwa Mandal, Swarnendu Ghosh, Teresa Gonçalves, Paulo Quaresma, Mita Nasipuri, Nibaran Das
Convolutional neural networks often generate multiple logits and use simple techniques like addition or averaging for loss computation.
no code implementations • 18 Aug 2020 • Bodhisatwa Mandal, Ritesh Sarkhel, Swarnendu Ghosh, Nibaran Das, Mita Nasipuri
To address this, we propose a novel two-phase dynamic routing protocol that computes agreements between neurons at various layers for micro and macro-level features, following a hierarchical learning paradigm.
no code implementations • 12 Mar 2020 • Soumyajyoti Dey, Soham Das, Swarnendu Ghosh, Shyamali Mitra, Sukanta Chakrabarty, Nibaran Das
One of the most challenging aspects of medical image analysis is the lack of a high quantity of annotated data.
no code implementations • 13 Jul 2019 • Swarnendu Ghosh, Nibaran Das, Ishita Das, Ujjwal Maulik
This paper approaches these various deep learning techniques of image segmentation from an analytical perspective.
no code implementations • 13 Jul 2019 • Bodhisatwa Mandal, Swarnendu Ghosh, Ritesh Sarkhel, Nibaran Das, Mita Nasipuri
Capsule networks have gained a lot of popularity in short time due to its unique approach to model equivariant class specific properties as capsules from images.
no code implementations • IEEE Applied Signal Processing Conference 2018 (ASPCON 2018) 2019 • Bodhisatwa Mandal, Suvam Dubey, Swarnendu Ghosh, Ritesh Sarkhel, Nibaran Das
Convolutional neural networks(CNNs) has become one of the primary algorithms for various computer vision tasks.
no code implementations • 14 Mar 2018 • Aritra Das, Swarnendu Ghosh, Ritesh Sarkhel, Sandipan Choudhuri, Nibaran Das, Mita Nasipuri
Modern deep learning algorithms have triggered various image segmentation approaches.
no code implementations • 5 Jan 2018 • Soumya Ukil, Swarnendu Ghosh, Sk Md Obaidullah, K. C. Santosh, Kaushik Roy, Nibaran Das
These are then used to train different CNNs to select features.