Giorgos Tolias

Global Average Precision for Representation Learning

Bill Psomas, Mohammad Mahdi, Michalis Thomas +3

Standard information retrieval metrics, such as mean Average Precision (mAP), assess performance one query at a time, based on how the similarities between a query and its positive…

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Vladan Stojnić, Ryan Ramos, Giorgos Kordopatis-Zilos +2

Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals. Prior work has focused on visible biases, such as object-background or texture correl…

Benchmarking Composed Image Retrieval for Applied Earth Observation

Bill Psomas, Dionysis Christopoulos, Thanasis Petropoulos +6

Remote sensing composed image retrieval (RSCIR) enables search in large satellite image archives using composed queries that combine a reference image with a textual modifier. Alth…

Indexing Multimodal Language Models for Large-scale Image Retrieval

Bahey Tharwat, Giorgos Kordopatis-Zilos, Pavel Suma +2

Multimodal Large Language Models (MLLMs) have demonstrated strong cross-modal reasoning capabilities, yet their potential for vision-only tasks remains underexplored. We investigat…

SPAR: Single-Pass Any-Resolution ViT for Open-vocabulary Segmentation

Naomi Kombol, Ivan Martinović, Siniša Šegvić +1

Foundational Vision Transformers (ViTs) have limited effectiveness in tasks requiring fine-grained spatial understanding, due to their fixed pre-training resolution and inherently…

ELViS: Efficient Visual Similarity from Local Descriptors that Generalizes Across Domains

Pavel Suma, Giorgos Kordopatis-Zilos, Yannis Kalantidis +1

Large-scale instance-level training data is scarce, so models are typically trained on domain-specific datasets. Yet in real-world retrieval, they must handle diverse domains, maki…

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

Tilemachos Aravanis, Vladan Stojnić, Bill Psomas +2

Open-vocabulary segmentation (OVS) extends the zero-shot recognition capabilities of vision-language models (VLMs) to pixel-level prediction, enabling segmentation of arbitrary cat…

Global-Aware Edge Prioritization for Pose Graph Initialization

Tong Wei, Giorgos Tolias, Jiri Matas +1

The pose graph is a core component of Structure-from-Motion (SfM), where images act as nodes and edges encode relative poses. Since geometric verification is expensive, SfM pipelin…

Instance-Level Composed Image Retrieval

Bill Psomas, George Retsinas, Nikos Efthymiadis +5

The progress of composed image retrieval (CIR), a popular research direction in image retrieval, where a combined visual and textual query is used, is held back by the absence of h…

Instance-Level Generation for Representation Learning

Yankun Wu, Zakaria Laskar, Giorgos Kordopatis-Zilos +2

Instance-level recognition (ILR) focuses on identifying individual objects rather than broad categories, offering the highest granularity in image classification. However, this fin…

Category-level Text-to-Image Retrieval Improved: Bridging the Domain Gap with Diffusion Models and Vision Encoders

Faizan Farooq Khan, Vladan Stojnić, Zakaria Laskar +2

This work explores text-to-image retrieval for queries that specify or describe a semantic category. While vision-and-language models (VLMs) like CLIP offer a straightforward open-…

Processing and acquisition traces in visual encoders: What does CLIP know about your camera?

Ryan Ramos, Vladan Stojnić, Giorgos Kordopatis-Zilos +3

Prior work has analyzed the robustness of visual encoders to image transformations and corruptions, particularly in cases where such alterations are not seen during training. When…

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

Bill Psomas, Dionysis Christopoulos, Eirini Baltzi +6

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 whos…

A Dataset for Semantic Segmentation in the Presence of Unknowns

Zakaria Laskar, Tomas Vojir, Matej Grcic +6

Before deployment in the real-world deep neural networks require thorough evaluation of how they handle both knowns, inputs represented in the training data, and unknowns (anomalie…

LOCORE: Image Re-ranking with Long-Context Sequence Modeling

Zilin Xiao, Pavel Suma, Ayush Sachdeva +4

We introduce LOCORE, Long-Context Re-ranker, a model that takes as input local descriptors corresponding to an image query and a list of gallery images and outputs similarity score…

LPOSS: Label Propagation Over Patches and Pixels for Open-vocabulary Semantic Segmentation

Vladan Stojnić, Yannis Kalantidis, Jiří Matas +1

We propose a training-free method for open-vocabulary semantic segmentation using Vision-and-Language Models (VLMs). Our approach enhances the initial per-patch predictions of VLMs…

ILIAS: Instance-Level Image retrieval At Scale

Giorgos Kordopatis-Zilos, Vladan Stojnić, Anna Manko +7

This work introduces ILIAS, a new test dataset for Instance-Level Image retrieval At Scale. It is designed to evaluate the ability of current and future foundation models and retri…

Three Things to Know about Deep Metric Learning

Yash Patel, Giorgos Tolias, Jiri Matas

This paper addresses supervised deep metric learning for open-set image retrieval, focusing on three key aspects: the loss function, mixup regularization, and model initialization.…

Composed Image Retrieval for Training-Free Domain Conversion

Nikos Efthymiadis, Bill Psomas, Zakaria Laskar +4

This work addresses composed image retrieval in the context of domain conversion, where the content of a query image is retrieved in the domain specified by the query text. We show…

Crafting Distribution Shifts for Validation and Training in Single Source Domain Generalization

Nikos Efthymiadis, Giorgos Tolias, Ondřej Chum

Single-source domain generalization attempts to learn a model on a source domain and deploy it to unseen target domains. Limiting access only to source domain data imposes two key…

AMES: Asymmetric and Memory-Efficient Similarity Estimation for Instance-level Retrieval

Pavel Suma, Giorgos Kordopatis-Zilos, Ahmet Iscen +1

This work investigates the problem of instance-level image retrieval re-ranking with the constraint of memory efficiency, ultimately aiming to limit memory usage to 1KB per image.…