6 papers
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…
Distilling Invariant Representations with Dual Augmentation
Nikolaos Giakoumoglou, 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…
A Review on Discriminative Self-supervised Learning Methods in Computer Vision
Nikolaos Giakoumoglou, Nikos Giakoumoglou, Tania Stathaki +1
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…
Discriminative and Consistent Representation Distillation
Nikolaos Giakoumoglou, 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…
SynCo: Synthetic Hard Negatives for Contrastive Visual Representation Learning
Nikolaos Giakoumoglou, Nikos Giakoumoglou, Tania Stathaki
Contrastive learning has become a dominant approach in self-supervised visual representation learning, but efficiently leveraging hard negatives, which are samples closely resembli…