AIConfPaper
← Search

Maria Vakalopoulou

8 accepted papers

2026

SoC: Semantic Orthogonal Calibration for Test-Time Prompt Tuning

Leo Fillioux, Omprakash Chakraborty, Ismail Ben Ayed, Paul-Henry Cournède, Stergios Christodoulidis, Maria Vakalopoulou +1
CVPR 2026

With the increasing adoption of vision-language models (VLMs) in critical decision-making systems such as in healthcare or autonomous driving, the calibration of their uncertainty estimates has become paramount. Yet, this dimension has been largely underexplored in the VLM test-time prompt-tuning (T

Cited by 0Source ↗code ↗Scholar ↗
2025

Controllable Latent Space Augmentation for Digital Pathology

Sofiène Boutaj, Marin Scalbert, Pierre Marza, Florent Couzinie-Devy, Maria Vakalopoulou, Stergios Christodoulidis
ICCV 2025poster

Whole slide image (WSI) analysis in digital pathology presents unique challenges due to the gigapixel resolution of WSIs and the scarcity of dense supervision signals. While Multiple Instance Learning (MIL) is a natural fit for slide-level tasks, training robust models requires large and diverse dat…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2025

THUNDER: Tile-level Histopathology image UNDERstanding benchmark

Pierre Marza, Leo Fillioux, Sofiène Boutaj, KUNAL MAHATHA, Christian Desrosiers, Pablo Piantanida +3
NeurIPS 2025spotlight

Progress in a research field can be hard to assess, in particular when many concurrent methods are proposed in a short period of time. This is the case in digital pathology, where many foundation models have been released recently to serve as feature extractors for tile-level images, being used in a…

Cited by 0Source ↗code ↗Scholar ↗
2024

SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathology

Saarthak Kapse, Pushpak Pati, Srijan Das, Jingwei Zhang, Chao Chen, Maria Vakalopoulou +4
CVPR 2024poster

Introducing interpretability and reasoning into Multiple Instance Learning (MIL) methods for Whole Slide Image (WSI) analysis is challenging given the complexity of gigapixel slides. Traditionally MIL interpretability is limited to identifying salient regions deemed pertinent for downstream tasks of…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization

Marin Scalbert, Maria Vakalopoulou, Florent Couzinie-Devy
ICLR 2024poster

In Self-Supervised Learning (SSL), models are typically pretrained, fine-tuned, and evaluated on the same domains. However, they tend to perform poorly when evaluated on unseen domains, a challenge that Unsupervised Domain Generalization (UDG) seeks to address. Current UDG methods rely on domain lab…

Cited by 4Source ↗PDF ↗Scholar ↗
2024

ViG-Bias: Visually Grounded Bias Discovery and Mitigation

Badr-Eddine Marani*, Mohamed Hanini, Nihitha Malayarukil, Stergios Christodoulidis, Maria Vakalopoulou, Enzo Ferrante
ECCV 2024poster

"The proliferation of machine learning models in critical decision-making processes has underscored the need for bias discovery and mitigation strategies. Identifying the reasons behind a biased system is not straightforward, since in many occasions they are associated with hidden spurious correlati…

Cited by 1Source ↗PDF ↗code ↗Scholar ↗
2024

You Don’t Need Domain-Specific Data Augmentations When Scaling Self-Supervised Learning

Théo Moutakanni, Maxime Oquab, Marc Szafraniec, Maria Vakalopoulou, Piotr Bojanowski
NeurIPS 2024poster

Self-Supervised learning (SSL) with Joint-Embedding Architectures (JEA) has led to outstanding performances. All instantiations of this paradigm were trained using strong and well-established hand-crafted data augmentations, leading to the general belief that they are required for the proper trainin…

Cited by 1Source ↗PDF ↗Scholar ↗
2023

Towards better certified segmentation via diffusion models

Othmane Laousy, Alexandre Araujo, Guillaume Chassagnon, Marie-Pierre Revel, Siddharth Garg, Farshad Khorrami +1
UAI 2023poster

The robustness of image segmentation has been an important research topic in the past few years as segmentation models have reached production-level accuracy. However, like classification models, segmentation models can be vulnerable to adversarial perturbations, which hinders their use in critical-…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗