51 citations · 170 across the 17 of their papers we have counts for
25 papers · 1 filter
Which Direction to Choose? An Analysis on the Representation Power of Self-Supervised ViTs in Downstream Tasks
Yannis Kaltampanidis, Alexandros Doumanoglou, Dimitrios Zarpalas
Self-Supervised Learning (SSL) for Vision Transformers (ViTs) has recently demonstrated considerable potential as a pre-training strategy for a variety of computer vision tasks, in…
Learning Encoding-Decoding Direction Pairs to Unveil Concepts of Influence in Deep Vision Networks
Alexandros Doumanoglou, Kurt Driessens, Dimitrios Zarpalas
Empirical evidence shows that deep vision networks often represent concepts as directions in latent space with concept information written along directional components in the vecto…
Unsupervised Interpretable Basis Extraction for Concept-Based Visual Explanations
Alexandros Doumanoglou, Stylianos Asteriadis, Dimitrios Zarpalas
An important line of research attempts to explain CNN image classifier predictions and intermediate layer representations in terms of human-understandable concepts. Previous work s…
Cross-Stitched Multi-task Dual Recursive Networks for Unified Single Image Deraining and Desnowing
Sotiris Karavarsamis, Alexandros Doumanoglou, Konstantinos Konstantoudakis +1
We present the Cross-stitched Multi-task Unified Dual Recursive Network (CMUDRN) model targeting the task of unified deraining and desnowing in a multi-task learning setting. This…
Hybrid Skip: A Biologically Inspired Skip Connection for the UNet Architecture
Nikolaos Zioulis, Georgios Albanis, Petros Drakoulis +3
In this work we introduce a biologically inspired long-range skip connection for the UNet architecture that relies on the perceptual illusion of hybrid images, being images that si…
Monocular Spherical Depth Estimation with Explicitly Connected Weak Layout Cues
Nikolaos Zioulis, Federico Alvarez, Dimitrios Zarpalas +1
Spherical cameras capture scenes in a holistic manner and have been used for room layout estimation. Recently, with the availability of appropriate datasets, there has also been pr…