no code implementations • 7 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.
no code implementations • 6 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.
no code implementations • 14 Feb 2021 • Sourav Mishra, Suresh Sundaram
This method is named significance-based distillation.
no code implementations • 15 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.
no code implementations • 26 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.
no code implementations • 11 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.