Search Results for author: Panagiotis Eustratiadis

Found 5 papers, 4 papers with code

Adversarial Augmentation Training Makes Action Recognition Models More Robust to Realistic Video Distribution Shifts

no code implementations21 Jan 2024 Kiyoon Kim, Shreyank N Gowda, Panagiotis Eustratiadis, Antreas Antoniou, Robert B Fisher

More precisely, we created dataset splits of HMDB-51 or UCF-101 for training, and Kinetics-400 for testing, using the subset of the classes that are overlapping in both train and test datasets.

Action Recognition Scheduling +2

Neural Fine-Tuning Search for Few-Shot Learning

1 code implementation15 Jun 2023 Panagiotis Eustratiadis, Łukasz Dudziak, Da Li, Timothy Hospedales

In few-shot recognition, a classifier that has been trained on one set of classes is required to rapidly adapt and generalize to a disjoint, novel set of classes.

Few-Shot Learning Neural Architecture Search

Attacking Adversarial Defences by Smoothing the Loss Landscape

1 code implementation1 Aug 2022 Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales

This paper investigates a family of methods for defending against adversarial attacks that owe part of their success to creating a noisy, discontinuous, or otherwise rugged loss landscape that adversaries find difficult to navigate.

Navigate

Weight-Covariance Alignment for Adversarially Robust Neural Networks

1 code implementation17 Oct 2020 Panagiotis Eustratiadis, Henry Gouk, Da Li, Timothy Hospedales

Stochastic Neural Networks (SNNs) that inject noise into their hidden layers have recently been shown to achieve strong robustness against adversarial attacks.

Adversarial Robustness

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