5 papers
Why Fake ? Unveiling the Semantic Vocabulary of Deepfake Detectors
Vazgken Vanian, Alexandros Doumanoglou, Dimitris Zarpalas
Deepfake (DF) technology poses a significant threat to information integrity, driving the need for robust detection methods. Most DF detectors only consider predicting a binary lab…
Compressing What Matters: Neuron Importance Meets Data-Aware Low Rank Approximation for Language Model Compression
Athanasios Ntovas, Alexandros Doumanoglou, Petros Drakoulis +1
To excel at their domain large language models are comprised of billions of parameters. Yet this comes at the cost of huge memory requirements restricting their applicability in re…
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…
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…