7 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…
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…
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…
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…