Nikos Komodakis

Retrieve and Segment: Are a Few Examples Enough to Bridge the Supervision Gap in Open-Vocabulary Segmentation?

arXiv 2026

Representations Before Pixels: Semantics-Guided Hierarchical Video Prediction

arXiv 2026

Coevolving Representations in Joint Image-Feature Diffusion

arXiv 2026

Boosting Generative Image Modeling via Joint Image-Feature Synthesis

arXiv 2025

ReplaceMe: Network Simplification via Layer Pruning and Linear Transformations

arXiv 2025

Multi-Token Prediction Needs Registers

arXiv 2025

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

CVPR 2025 1

Attention, Please! Revisiting Attentive Probing for Masked Image Modeling

arXiv 2025

$\texttt{DINO-Foresight}$: Looking into the Future with DINO

arXiv 2024

SPOT: Self-Training with Patch-Order Permutation for Object-Centric Learning with Autoregressive Transformers

CVPR 2024 1

What to Hide from Your Students: Attention-Guided Masked Image Modeling

arXiv 2022

OBoW: Online Bag-of-Visual-Words Generation for Self-Supervised Learning

obow-online-bag-of-visual-words-generation

Unsupervised Representation Learning by Predicting Image Rotations

unsupervised-representation-learning-by-2

Wide Residual Networks

arXiv 2016

Spyros Gidaris

Ioannis Kakogeorgiou

Efstathios Karypidis

Bill Psomas

Konstantinos Karantzalos

Andrei Bursuc

Giorgos Tolias

Sergey Zagoruyko

Theodoros Kouzelis

Tilemachos Aravanis