Nikos Komodakis — accepted AI-conference papers

2026

Attention, Please! Revisiting Attentive Probing Through the Lens of Efficiency

Bill Psomas, Dionysis Christopoulos, Eirini Baltzi, Ioannis Kakogeorgiou, Tilemachos Aravanis, Nikos Komodakis +3

ICLR 2026poster

As fine-tuning becomes impractical at scale, probing is emerging as the preferred evaluation protocol. However, standard linear probing can understate the capability of models whose pre-training optimizes local representations rather than an explicit global representation. This motivates attentive p…

Cited by 0 Source ↗code ↗Scholar ↗

2026

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

Tilemachos Aravanis, Vladan Stojnić, Bill Psomas, Nikos Komodakis, Giorgos Tolias

CVPR 2026

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary categories specified by text prompts. Despite recent progress, OVS lags behind fully supervised approaches due to two chall

Cited by 0 Source ↗code ↗Scholar ↗

2025

Advancing Semantic Future Prediction through Multimodal Visual Sequence Transformers

Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis

CVPR 2025poster

Semantic future prediction is important for autonomous systems navigating dynamic environments. This paper introduces FUTURIST, a method for multimodal future semantic prediction that uses a unified and efficient visual sequence transformer architecture. Our approach incorporates a multimodal masked…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2025

Boosting Generative Image Modeling via Joint Image-Feature Synthesis

Theodoros Kouzelis, Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis

NeurIPS 2025spotlight

Latent diffusion models (LDMs) dominate high-quality image generation, yet integrating representation learning with generative modeling remains a challenge. We introduce a novel generative image modeling framework that seamlessly bridges this gap by leveraging a diffusion model to jointly model low-…

Cited by 0 Source ↗Scholar ↗

2025

DINO-Foresight: Looking into the Future with DINO

Efstathios Karypidis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis

NeurIPS 2025poster

Predicting future dynamics is crucial for applications like autonomous driving and robotics, where understanding the environment is key. Existing pixel-level methods are computationally expensive and often focus on irrelevant details. To address these challenges, we introduce DINO-Foresight, a nove…

Cited by 0 Source ↗Scholar ↗

2025

EQ-VAE: Equivariance Regularized Latent Space for Improved Generative Image Modeling

Theodoros Kouzelis, Ioannis Kakogeorgiou, Spyros Gidaris, Nikos Komodakis

ICML 2025poster

Latent generative models have emerged as a leading approach for high-quality image synthesis. These models rely on an autoencoder to compress images into a latent space, followed by a generative model to learn the latent distribution. We identify that existing autoencoders lack equivariance to seman…

Cited by 5 Source ↗PDF ↗Scholar ↗

2025

Multi-Token Prediction Needs Registers

Anastasios Gerontopoulos, Spyros Gidaris, Nikos Komodakis

NeurIPS 2025poster

Multi-token prediction has emerged as a promising objective for improving language model pretraining, but its benefits have not consistently generalized to other settings such as fine-tuning. In this paper, we propose MuToR, a simple and effective approach to multi-token prediction that interleaves…

Cited by 0 Source ↗code ↗Scholar ↗

2025

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization

Dmitriy Shopkhoev, Ammar Ali, Magauiya Zhussip, Valentin Malykh, Stamatios Lefkimmiatis, Nikos Komodakis +1

NeurIPS 2025poster

We introduce ReplaceMe, a generalized training-free depth pruning method that effectively replaces transformer blocks with a linear operation, while maintaining high performance for low compression ratios. In contrast to conventional pruning approaches that require additional training or fine-tuning…

Cited by 0 Source ↗code ↗Scholar ↗

2024

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

Ioannis Kakogeorgiou, Spyros Gidaris, Konstantinos Karantzalos, Nikos Komodakis

CVPR 2024highlight

Unsupervised object-centric learning aims to decompose scenes into interpretable object entities termed slots. Slot-based auto-encoders stand out as a prominent method for this task. Within them crucial aspects include guiding the encoder to generate object-specific slots and ensuring the decoder ut…

Cited by 14 Source ↗PDF ↗code ↗Scholar ↗

2024

ToNNO: Tomographic Reconstruction of a Neural Network's Output for Weakly Supervised Segmentation of 3D Medical Images

Marius Schmidt-Mengin, Alexis Benichoux, Shibeshih Belachew, Nikos Komodakis, Nikos Paragios

CVPR 2024poster

Annotating lots of 3D medical images for training segmentation models is time-consuming. The goal of weakly supervised semantic segmentation is to train segmentation models without using any ground truth segmentation masks. Our work addresses the case where only image-level categorical labels indica…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

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

Ioannis Kakogeorgiou, Spyros Gidaris, Bill Psomas, Yannis Avrithis, Andrei Bursuc, Konstantinos Karantzalos +1

ECCV 2022poster

"Transformers and masked language modeling are quickly being adopted and explored in computer vision as vision transformers and masked image modeling (MIM). In this work, we argue that image token masking differs from token masking in text, due to the amount and correlation of tokens in an image. In…

Cited by 146 Source ↗PDF ↗code ↗Scholar ↗

2021

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

Spyros Gidaris, Andrei Bursuc, Gilles Puy, Nikos Komodakis, Matthieu Cord, Patrick Perez

CVPR 2021poster

Learning image representations without human supervision is an important and active research field. Several recent approaches have successfully leveraged the idea of making such a representation invariant under different types of perturbations, especially via contrastive-based instance discriminatio…

Cited by 125 PDF ↗code ↗Scholar ↗

2020

Learning Representations by Predicting Bags of Visual Words

Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Perez, Matthieu Cord

CVPR 2020poster

Self-supervised representation learning targets to learn convnet-based image representations from unlabeled data. Inspired by the success of NLP methods in this area, in this work we propose a self-supervised approach based on spatially dense image descriptions that encode discrete visual concepts,…

Cited by 132 PDF ↗code ↗Scholar ↗

2020

QuEST: Quantized Embedding Space for Transferring Knowledge

Himalaya Jain, Spyros Gidaris, Nikos Komodakis, Patrick Pérez, Matthieu Cord

ECCV 2020poster

Knowledge distillation refers to the process of training a student network to achieve better accuracy by learning from a pre-trained teacher network. Most of the existing knowledge distillation methods direct the student to follow the teacher by matching the teacher's output, feature maps or their d…

Cited by 12 Source ↗PDF ↗Scholar ↗

2019

Boosting Few-Shot Visual Learning With Self-Supervision

Spyros Gidaris, Andrei Bursuc, Nikos Komodakis, Patrick Perez, Matthieu Cord

ICCV 2019poster

Few-shot learning and self-supervised learning address different facets of the same problem: how to train a model with little or no labeled data. Few-shot learning aims for optimization methods and models that can learn efficiently to recognize patterns in the low data regime. Self-supervised learni…

Cited by 511 PDF ↗code ↗Scholar ↗

2019

Generating Classification Weights With GNN Denoising Autoencoders for Few-Shot Learning

Spyros Gidaris, Nikos Komodakis

CVPR 2019oral

Given an initial recognition model already trained on a set of base classes, the goal of this work is to develop a meta-model for few-shot learning. The meta-model, given as input some novel classes with few training examples per class, must properly adapt the existing recognition model into a new m…

Cited by 332 PDF ↗code ↗Scholar ↗

2018

Dynamic Few-Shot Visual Learning Without Forgetting

Spyros Gidaris, Nikos Komodakis

CVPR 2018poster

The human visual system has the remarkably ability to be able to effortlessly learn novel concepts from only a few examples. Mimicking the same behavior on machine learning vision systems is an interesting and very challenging research problem with many practical advantages on real world vision appl…

Cited by 1450 Source ↗PDF ↗code ↗Scholar ↗

2018

Unsupervised Representation Learning by Predicting Image Rotations

Spyros Gidaris, Praveer Singh, Nikos Komodakis

ICLR 2018poster

Over the last years, deep convolutional neural networks (ConvNets) have transformed the field of computer vision thanks to their unparalleled capacity to learn high level semantic image features. However, in order to successfully learn those features, they usually require massive amounts of manuall…

Cited by 4239 Source ↗PDF ↗code ↗Scholar ↗

2017

Detect, Replace, Refine: Deep Structured Prediction for Pixel Wise Labeling

Spyros Gidaris, Nikos Komodakis

CVPR 2017poster

Pixel wise image labeling is an interesting and challenging problem with great significance in the computer vision community. In order for a dense labeling algorithm to be able to achieve accurate and precise results, it has to consider the dependencies that exist in the joint space of both the inpu…

Cited by 195 PDF ↗code ↗Scholar ↗

2017

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

Martin Simonovsky, Nikos Komodakis

CVPR 2017spotlight

A number of problems can be formulated as prediction on graph-structured data. In this work, we generalize the convolution operator from regular grids to arbitrary graphs while avoiding the spectral domain, which allows us to handle graphs of varying size and connectivity. To move beyond a simple di…

Cited by 1648 PDF ↗code ↗Scholar ↗

2017

Newton-Type Methods for Inference in Higher-Order Markov Random Fields

Hariprasad Kannan, Nikos Komodakis, Nikos Paragios

CVPR 2017poster

Linear programming relaxations are central to MAP in- ference in discrete Markov Random Fields. The ability to properly solve the Lagrangian dual is a critical component of such methods. In this paper, we study the benefit of us- ing Newton-type methods to solve the Lagrangian dual of a smooth versi…

Cited by 3 PDF ↗Scholar ↗

2017

Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer

Sergey Zagoruyko, Nikos Komodakis

ICLR 2017poster

Attention plays a critical role in human visual experience. Furthermore, it has recently been demonstrated that attention can also play an important role in the context of applying artificial neural networks to a variety of tasks from fields such as computer vision and NLP. In this work we show that…

Cited by 3439 Source ↗code ↗Scholar ↗

2017

Rotation Equivariant Vector Field Networks

Diego Marcos, Michele Volpi, Nikos Komodakis, Devis Tuia

ICCV 2017poster

In many computer vision tasks, we expect a particular behavior of the output with respect to rotations of the input image. If this relationship is explicitly encoded, instead of treated as any other variation, the complexity of the problem is decreased, leading to a reduction in the size of the requ…

Cited by 323 PDF ↗code ↗Scholar ↗

2016

LocNet: Improving Localization Accuracy for Object Detection

Spyros Gidaris, Nikos Komodakis

CVPR 2016oral

We propose a novel object localization methodology with the purpose of boosting the localization accuracy of state-of-the-art object detection systems. Our model, given a search region, aims at returning the bounding box of an object of interest inside this region. To accomplish its goal, it relies…

Cited by 180 PDF ↗code ↗Scholar ↗

2015

HARF: Hierarchy-Associated Rich Features for Salient Object Detection

Wenbin Zou, Nikos Komodakis

ICCV 2015poster

The state-of-the-art salient object detection models are able to perform well for relatively simple scenes, yet for more complex ones, they still have difficulties in highlighting salient objects completely from background, largely due to the lack of sufficiently robust features for saliency predict…

Cited by 78 PDF ↗Scholar ↗

2015

Learning to Compare Image Patches via Convolutional Neural Networks

Sergey Zagoruyko, Nikos Komodakis

CVPR 2015poster

In this paper we show how to learn directly from image data (i.e., without resorting to manually-designed features) a general similarity function for comparing image patches, which is a task of fundamental importance for many computer vision problems. To encode such a function, we opt for a CNN-bas…

Cited by 1924 Source ↗PDF ↗code ↗Scholar ↗

2015

Object Detection via a Multi-Region and Semantic Segmentation-Aware CNN Model

Spyros Gidaris, Nikos Komodakis

ICCV 2015poster

We propose an object detection system that relies on a multi-region deep convolutional neural network (CNN) that also encodes semantic segmentation-aware features. The resulting CNN-based representation aims at capturing a diverse set of discriminative appearance factors and exhibits localization se…

Cited by 1043 PDF ↗code ↗Scholar ↗