no code implementations • 29 Mar 2024 • Amitangshu Mukherjee, Timur Ibrayev, Kaushik Roy
Current Deep Neural Networks are vulnerable to adversarial examples, which alter their predictions by adding carefully crafted noise.
no code implementations • 24 Mar 2024 • Timur Ibrayev, Amitangshu Mukherjee, Sai Aparna Aketi, Kaushik Roy
Specifically, the proposed framework models the following mechanisms: 1) ventral (what) stream focusing on the input regions perceived by the fovea part of an eye (foveation), 2) dorsal (where) stream providing visual guidance, and 3) iterative processing of the two streams to calibrate visual focus and process the sequence of focused image patches.
no code implementations • 20 Dec 2021 • Amitangshu Mukherjee, Isha Garg, Kaushik Roy
We show that learning in this structured hierarchical manner results in networks that are more robust against subpopulation shifts, with an improvement up to 3\% in terms of accuracy and up to 11\% in terms of graphical distance over standard models on subpopulation shift benchmarks.
1 code implementation • ICCV 2019 • Ameya Joshi, Amitangshu Mukherjee, Soumik Sarkar, Chinmay Hegde
We propose a novel approach to generate such `semantic' adversarial examples by optimizing a particular adversarial loss over the range-space of a parametric conditional generative model.