collaborators

12 papers

cs.CV2026

Three Necessary Principles for Self-Supervised Visual Representation Learning

Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki

We argue that learning visual representations without labels requires a training signal jointly complete across three non-overlapping objectives: semantic invariance across augment…

cs.CV2026

Open-World Semantic Segmentation with Sensitivity Modeling

Anastasios Romanos Varvarigos, Nikos Giakoumoglou, Tania Stathaki

Modern vision systems must operate in "open-world" settings, where models must recognize known categories and detect unseen or anomalous content. Conventional semantic segmentation…

cs.CV2026

Caption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval

Lucas Iijima, Nikolaos Giakoumoglou, Nikos Giakoumoglou +1

Cross-Domain Image Retrieval (CDIR) is a challenging task in computer vision, aiming to match images across different visual domains such as sketches, paintings, and photographs. E…

cs.CV2025

Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives

Nikolaos Giakoumoglou, Nikos Giakoumoglou, Andreas Floros +2

This paper does not introduce a new method per se. Instead, we build on existing self-supervised learning approaches for vision, drawing inspiration from the adage "fake it till yo…

cs.CV2025

Unsupervised Training of Vision Transformers with Synthetic Negatives

Nikolaos Giakoumoglou, Nikos Giakoumoglou, Andreas Floros +2

This paper does not introduce a novel method per se. Instead, we address the neglected potential of hard negative samples in self-supervised learning. Previous works explored synth…

cs.CV2025

Cluster Contrast for Unsupervised Visual Representation Learning

Nikolaos Giakoumoglou, Nikos Giakoumoglou, Tania Stathaki

We introduce Cluster Contrast (CueCo), a novel approach to unsupervised visual representation learning that effectively combines the strengths of contrastive learning and clusterin…