activity
20182022
most citedLocal Competition and Uncertainty for Adversarial Robustness in Deep Learning

1 citations · 2 across the 4 of their papers we have counts for

collaborators

6 papers

cs.LG2022

Competing Mutual Information Constraints with Stochastic Competition-based Activations for Learning Diversified Representations

Konstantinos P. Panousis, Anastasios Antoniadis, Sotirios Chatzis

This work aims to address the long-established problem of learning diversified representations. To this end, we combine information-theoretic arguments with stochastic competition-…

cs.CL2021

Stochastic Transformer Networks with Linear Competing Units: Application to end-to-end SL Translation

Andreas Voskou, Konstantinos P. Panousis, Dimitrios Kosmopoulos +2

Automating sign language translation (SLT) is a challenging real world application. Despite its societal importance, though, research progress in the field remains rather poor. Cru…

cs.CL2021

Dialog speech sentiment classification for imbalanced datasets

Sergis Nicolaou, Lambros Mavrides, Georgina Tryfou +4

Speech is the most common way humans express their feelings, and sentiment analysis is the use of tools such as natural language processing and computational algorithms to identify…

cs.LG20211 cited

Local Competition and Stochasticity for Adversarial Robustness in Deep Learning

Konstantinos P. Panousis, Sotirios Chatzis, Antonios Alexos +1

This work addresses adversarial robustness in deep learning by considering deep networks with stochastic local winner-takes-all (LWTA) activations. This type of network units resul…

cs.LG20201 cited

Local Competition and Uncertainty for Adversarial Robustness in Deep Learning

Antonios Alexos, Konstantinos P. Panousis, Sotirios Chatzis

This work attempts to address adversarial robustness of deep networks by means of novel learning arguments. Specifically, inspired from results in neuroscience, we propose a local…

cs.LG2018

Nonparametric Bayesian Deep Networks with Local Competition

Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis

The aim of this work is to enable inference of deep networks that retain high accuracy for the least possible model complexity, with the latter deduced from the data during inferen…