5 papers
DISCOVER: Making Vision Networks Interpretable via Competition and Dissection
Konstantinos P. Panousis, Sotirios Chatzis
Modern deep networks are highly complex and their inferential outcome very hard to interpret. This is a serious obstacle to their transparent deployment in safety-critical or bias-…
A New Dataset for End-to-End Sign Language Translation: The Greek Elementary School Dataset
Andreas Voskou, Konstantinos P. Panousis, Harris Partaourides +2
Automatic Sign Language Translation (SLT) is a research avenue of great societal impact. End-to-End SLT facilitates the interaction of Hard-of-Hearing (HoH) with hearing people, th…
Sparse Linear Concept Discovery Models
Konstantinos P. Panousis, Dino Ienco, Diego Marcos
The recent mass adoption of DNNs, even in safety-critical scenarios, has shifted the focus of the research community towards the creation of inherently intrepretable models. Concep…
Macroeconomic forecasting and sovereign risk assessment using deep learning techniques
Anastasios Petropoulos, Vassilis Siakoulis, Konstantinos P. Panousis +2
In this study, we propose a novel approach of nowcasting and forecasting the macroeconomic status of a country using deep learning techniques. We focus particularly on the US econo…
Stochastic Local Winner-Takes-All Networks Enable Profound Adversarial Robustness
Konstantinos P. Panousis, Sotirios Chatzis, Sergios Theodoridis
This work explores the potency of stochastic competition-based activations, namely Stochastic Local Winner-Takes-All (LWTA), against powerful (gradient-based) white-box and black-b…