1 code implementation • 27 Feb 2023 • Prashant Pandey, Mustafa Chasmai, Monish Natarajan, Brejesh lall
To this end, we propose a novel unified weakly supervised OVSS pipeline that can perform ZSS, FSS and Cross-dataset segmentation on novel classes without using pixel-level labels for either the base (seen) or the novel (unseen) classes in an inductive setting.
no code implementations • 26 Nov 2022 • Britty Baby, Daksh Thapar, Mustafa Chasmai, Tamajit Banerjee, Kunal Dargan, Ashish Suri, Subhashis Banerjee, Chetan Arora
Minimally invasive surgeries and related applications demand surgical tool classification and segmentation at the instance level.
1 code implementation • 7 Oct 2022 • Prashant Pandey, Aleti Vardhan, Mustafa Chasmai, Tanuj Sur, Brejesh lall
We show that our framework is more robust compared to traditional adversarial defense mechanisms such as adversarial training.
1 code implementation • 26 Aug 2022 • Prashant Pandey, Mustafa Chasmai, Tanuj Sur, Brejesh lall
We further demonstrate that while many existing Deep CNN based methods tend to be extremely vulnerable to adversarial attacks, R-PNODE exhibits increased adversarial robustness for a wide array of these attacks.
no code implementations • 27 Jun 2022 • Mustafa Chasmai, Nirjhar Das, Aman Bhardwaj, Rahul Garg
We argue that for most of the applications, validation accuracies on unseen subjects and unseen camera angles would be most important.
1 code implementation • 17 Jun 2021 • Haiping Lu, Xianyuan Liu, Robert Turner, Peizhen Bai, Raivo E Koot, Shuo Zhou, Mustafa Chasmai, Lawrence Schobs
Machine learning is a general-purpose technology holding promises for many interdisciplinary research problems.