Search Results for author: Sourav Mishra

Found 6 papers, 0 papers with code

Towards Improved Imbalance Robustness in Continual Multi-Label Learning with Dual Output Spiking Architecture (DOSA)

no code implementations7 Feb 2024 Sourav Mishra, Shirin Dora, Suresh Sundaram

A novel imbalance-aware loss function is also proposed, improving the multi-label classification performance of the model by making it more robust to data imbalance.

Multi-Label Classification Multi-Label Learning

Confidence Conditioned Knowledge Distillation

no code implementations6 Jul 2021 Sourav Mishra, Suresh Sundaram

Distillation through CCKD methods improves the resilience of the student models against adversarial attacks compared to the conventional KD method.

Knowledge Distillation

Assessing Robustness of Deep learning Methods in Dermatological Workflow

no code implementations15 Jan 2020 Sourav Mishra, Subhajit Chaudhury, Hideaki Imaizumi, Toshihiko Yamasaki

This paper aims to evaluate the suitability of current deep learning methods for clinical workflow especially by focusing on dermatology.

Improving image classifiers for small datasets by learning rate adaptations

no code implementations26 Mar 2019 Sourav Mishra, Toshihiko Yamasaki, Hideaki Imaizumi

Our paper introduces an efficient combination of established techniques to improve classifier performance, in terms of accuracy and training time.

Supervised classification of Dermatological diseases by Deep learning

no code implementations11 Feb 2018 Sourav Mishra, Toshihiko Yamasaki, Hideaki Imaizumi

This paper introduces a deep-learning based efficient classifier for common dermatological conditions, aimed at people without easy access to skin specialists.

Classification General Classification

Cannot find the paper you are looking for? You can Submit a new open access paper.