232 citations · 235 across the 12 of their papers we have counts for
17 papers
Quantitative symplectic topology of Katok's examples and equivariant symplectic embeddings
Nikolas Adaloglou, Johannes Hauber
The Katok examples on are induced by Randers metrics obtained by perturbing the round metric by the standard rotational Killing field: allowing a scaling factor of the round…
The nearby Lagrangian conjecture for pinwheels
Nikolas Adaloglou, Gerard Bargalló i Gómez, Johannes Hauber
The Lagrangian skeleton of the rational homology ball , for coprime integers, is an immersed but not embedded Lagrangian, called a -pinwheel. We show that a…
ClusterMine: Robust Label-Free Visual Out-Of-Distribution Detection via Concept Mining from Text Corpora
Nikolas Adaloglou, Diana Petrusheva, Mohamed Asker +2
Large-scale visual out-of-distribution (OOD) detection has witnessed remarkable progress by leveraging vision-language models such as CLIP. However, a significant limitation of cur…
Markov staircases
Nikolas Adaloglou, Joé Brendel, Jonny Evans +2
Rational homology ellipsoids are certain Liouville domains diffeomorphic to rational homology balls and having Lagrangian pin-wheels as their skeleta. From the point of view of alm…
Pinwheels in symplectic rational and ruled surfaces and non-squeezing of rational homology balls
Nikolas Adaloglou, Johannes Hauber
We use almost toric fibrations and the symplectic rational blow-up to determine when certain Lagrangian pinwheels, which we call liminal, embed in symplectic rational and ruled sur…
Guiding a diffusion model using sliding windows
Nikolas Adaloglou, Tim Kaiser, Damir Iagudin +1
Guidance is a widely used technique for diffusion models to enhance sample quality. Technically, guidance is realised by using an auxiliary model that generalises more broadly than…
Lagrangian Klein bottles in
Nikolas Adaloglou, Jonathan David Evans
We use Luttinger surgery to show that there are no Lagrangian Klein bottles in in the -homology class of an -factor if the symplectic area of tha…
Scaling Up Deep Clustering Methods Beyond ImageNet-1K
Nikolas Adaloglou, Felix Michels, Kaspar Senft +2
Deep image clustering methods are typically evaluated on small-scale balanced classification datasets while feature-based -means has been applied on proprietary billion-scale da…
Embeddings and disjunction of Lagrangian pinwheels via rational blow-ups
Nikolas Adaloglou
We use the symplectic rational blow-up to study some Lagrangian pinwheels in symplectic rational manifolds. In particular, we determine which symplectic forms in the threefold blow…
Symplectic cohomology of quasihomogeneous singularities
Nikolas Adaloglou, Federica Pasquotto, Aline Zanardini
We compute the symplectic cohomology of Milnor fibers of isolated quasihomogeneous cAn singularities . In addition, we use our computations to distinguish their links as contact ma…
Rethinking cluster-conditioned diffusion models for label-free image synthesis
Nikolas Adaloglou, Tim Kaiser, Felix Michels +1
Diffusion-based image generation models can enhance image quality when conditioned on ground truth labels. Here, we conduct a comprehensive experimental study on image-level condit…
Exploring the Limits of Deep Image Clustering using Pretrained Models
Nikolas Adaloglou, Felix Michels, Hamza Kalisch +1
We present a general methodology that learns to classify images without labels by leveraging pretrained feature extractors. Our approach involves self-distillation training of clus…
Adapting Contrastive Language-Image Pretrained (CLIP) Models for Out-of-Distribution Detection
Nikolas Adaloglou, Felix Michels, Tim Kaiser +1
We present a comprehensive experimental study on pretrained feature extractors for visual out-of-distribution (OOD) detection, focusing on adapting contrastive language-image pretr…
Self-Supervised Anomaly Detection by Self-Distillation and Negative Sampling
Nima Rafiee, Rahil Gholamipoorfard, Nikolas Adaloglou +3
Detecting whether examples belong to a given in-distribution or are Out-Of-Distribution (OOD) requires identifying features specific to the in-distribution. In the absence of label…
Uniqueness of Lagrangians in
Nikolaos Adaloglou
We present a new and simpler proof of the fact that any Lagrangian in is Hamiltonian isotopic to the zero section. Our proof mirrors the one give…
Multi-view adaptive graph convolutions for graph classification
Nikolas Adaloglou, Nicholas Vretos, Petros Daras
In this paper, a novel multi-view methodology for graph-based neural networks is proposed. A systematic and methodological adaptation of the key concepts of classical deep learning…
A Comprehensive Study on Deep Learning-based Methods for Sign Language Recognition
Nikolas Adaloglou, Theocharis Chatzis, Ilias Papastratis +7
In this paper, a comparative experimental assessment of computer vision-based methods for sign language recognition is conducted. By implementing the most recent deep neural networ…