4 citations · 6 across the 15 of their papers we have counts for
14 papers · 1 filter
Generalizable AI-Generated Image Detection with Embedding-Space Explanations
Nikos Giakoumoglou, Paschalis Giakoumoglou, Tania Stathaki +1
AI-generated images have reached unprecedented realism, while instruction-driven AI editors re-synthesize images for local changes, leaving no splice boundary to localize. Most det…
What Makes Synthetic Hard Negatives Work in Vision-Language Pretraining?
Nikos Giakoumoglou, Paschalis Giakoumoglou, Andreas Floros +2
Synthetic hard negatives generated in the representation space have proven effective for unimodal self-supervised learning, but transferring this idea to vision-language pretrainin…
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…
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…
ViTAMINS: An Empirical Study of Training Self-Supervised Vision Transformers with Synthetic Hard Negatives
Nikos Giakoumoglou, Andreas Floros, Kleanthis-Marios Papadopoulos +1
We introduce ViTAMINS, a method that integrates synthetic hard negatives into unsupervised vision transformer pretraining to improve representation quality. Our approach is thoroug…
Fake & Square: Training Self-Supervised Vision Transformers with Synthetic Data and Synthetic Hard Negatives
Nikos Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos +1
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…
Unsupervised Training of Vision Transformers with Synthetic Negatives
Nikos Giakoumoglou, Andreas Floros, Kleanthis Marios Papadopoulos +1
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…
Cluster Contrast for Unsupervised Visual Representation Learning
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…
Distilling Invariant Representations with Dual Augmentation
Nikos Giakoumoglou, Tania Stathaki
Knowledge distillation (KD) has been widely used to transfer knowledge from large, accurate models (teachers) to smaller, efficient ones (students). Recent methods have explored en…
SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learning
Nikos Giakoumoglou, Tania Stathaki
Contrastive learning relies on informative negatives to shape the representation space, yet obtaining hard negatives is costly, often requiring large batch sizes or extensive memor…
Relational Representation Distillation
Nikos Giakoumoglou, Tania Stathaki
Knowledge distillation transfers knowledge from large teacher models to more compact student networks. The standard approach minimizes the Kullback-Leibler (KL) divergence between…
Discriminative and Consistent Representation Distillation
Nikos Giakoumoglou, Tania Stathaki
Knowledge Distillation (KD) transfers knowledge from a large teacher to a smaller student model. While contrastive objectives have proven effective for learning structured represen…
A Review on Discriminative Self-supervised Learning Methods in Computer Vision
Nikos Giakoumoglou, Tania Stathaki, Athanasios Gkelias
Self-supervised learning (SSL) has rapidly emerged as a transformative approach in computer vision, enabling the extraction of rich feature representations from vast amounts of unl…
Caption-Matching: A Multimodal Approach for Cross-Domain Image Retrieval
Lucas Iijima, Nikos Giakoumoglou, Tania Stathaki
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…