AIConfPaper
← Search

Yannis Avrithis

25 accepted 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 0Source ↗code ↗Scholar ↗
2026

DEEP TPC: TEMPORAL-PRIOR CONDITIONING FOR TIME SERIES FORECASTING

Filippos Bellos, Yannis Avrithis, Nam Nguyen, Jason Corso
ICASSP 2026oral

LLM-for-time series (TS) methods typically treat time shallowly, injecting positional or prompt-based cues once at the input of a largely frozen decoder, which limits temporal reasoning as this information degrades through the layers. We introduce Temporal-Prior Conditioning (TPC), which elevates ti…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Instance-Level Composed Image Retrieval

Bill Psomas, George Retsinas, Nikos Efthymiadis, Panagiotis Filntisis, Yannis Avrithis, Petros Maragos +2
NeurIPS 2025poster

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 high-quality training and evaluation data. We introduce a new evaluation dataset, i-CIR, which, unlike existing datasets,…

Cited by 0Source ↗Scholar ↗
2024

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

Shashanka Venkataramanan, Mamshad Nayeem Rizve, Joao Carreira, Yuki M Asano, Yannis Avrithis
ICLR 2024oral

Self-supervised learning has unlocked the potential of scaling up pretraining to billions of images, since annotation is unnecessary. But are we making the best use of data? How more economical can we be? In this work, we attempt to answer this question by making two contributions. First, we investi…

Cited by 22Source ↗PDF ↗Scholar ↗
2024

On Train-Test Class Overlap and Detection for Image Retrieval

Chull Hwan Song, Jooyoung Yoon, Taebaek Hwang, Shunghyun Choi, Yeong Hyeon Gu, Yannis Avrithis
CVPR 2024poster

How important is it for training and evaluation sets to not have class overlap in image retrieval? We revisit Google Landmarks v2 clean the most popular training set by identifying and removing class overlap with Revisited Oxford and Paris the most popular training set. By comparing the original and…

Cited by 7Source ↗PDF ↗Scholar ↗
2023

Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples

Shashanka Venkataramanan, Ewa Kijak, laurent amsaleg, Yannis Avrithis
NeurIPS 2023poster

Mixup refers to interpolation-based data augmentation, originally motivated as a way to go beyond empirical risk minimization (ERM). Its extensions mostly focus on the definition of interpolation and the space (input or feature) where it takes place, while the augmentation process itself is less stu…

Cited by 6Source ↗PDF ↗Scholar ↗
2023

Generating Part-Aware Editable 3D Shapes Without 3D Supervision

Konstantinos Tertikas, Despoina Paschalidou, Boxiao Pan, Jeong Joon Park, Mikaela Angelina Uy, Ioannis Emiris +2
CVPR 2023poster

Impressive progress in generative models and implicit representations gave rise to methods that can generate 3D shapes of high quality. However, being able to locally control and edit shapes is another essential property that can unlock several content creation applications. Local control can be ach…

Cited by 39Source ↗PDF ↗code ↗Scholar ↗
2023

Keep It SimPool: Who Said Supervised Transformers Suffer from Attention Deficit?

Bill Psomas, Ioannis Kakogeorgiou, Konstantinos Karantzalos, Yannis Avrithis
ICCV 2023poster

Convolutional networks and vision transformers have different forms of pairwise interactions, pooling across layers and pooling at the end of the network. Does the latter really need to be different? As a by-product of pooling, vision transformers provide spatial attention for free, but this is mos…

Cited by 12PDF ↗code ↗Scholar ↗
2022

AlignMixup: Improving Representations by Interpolating Aligned Features

Shashanka Venkataramanan, Ewa Kijak, Laurent Amsaleg, Yannis Avrithis
CVPR 2022poster

Mixup is a powerful data augmentation method that interpolates between two or more examples in the input or feature space and between the corresponding target labels. However, how to best interpolate images is not well defined. Recent mixup methods overlay or cut-and-paste two or more objects into o…

Cited by 95PDF ↗code ↗Scholar ↗
2022

It Takes Two to Tango: Mixup for Deep Metric Learning

Shashanka Venkataramanan, Bill Psomas, Ewa Kijak, laurent amsaleg, Konstantinos Karantzalos, Yannis Avrithis
ICLR 2022poster

Metric learning involves learning a discriminative representation such that embeddings of similar classes are encouraged to be close, while embeddings of dissimilar classes are pushed far apart. State-of-the-art methods focus mostly on sophisticated loss functions or mining strategies. On the one ha…

Cited by 38Source ↗PDF ↗code ↗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 146Source ↗PDF ↗code ↗Scholar ↗
2021

Iterative Label Cleaning for Transductive and Semi-Supervised Few-Shot Learning

Michalis Lazarou, Tania Stathaki, Yannis Avrithis
ICCV 2021poster

Few-shot learning amounts to learning representations and acquiring knowledge such that novel tasks may be solved with both supervision and data being limited. Improved performance is possible by transductive inference, where the entire test set is available concurrently, and semi-supervised learnin…

Cited by 89PDF ↗code ↗Scholar ↗
2021

On the Hidden Treasure of Dialog in Video Question Answering

Deniz Engin, François Schnitzler, Ngoc Q. K. Duong, Yannis Avrithis
ICCV 2021poster

High-level understanding of stories in video such as movies and TV shows from raw data is extremely challenging. Modern video question answering (VideoQA) systems often use additional human-made sources like plot synopses, scripts, video descriptions or knowledge bases. In this work, we present a ne…

Cited by 12PDF ↗code ↗Scholar ↗
2020

Graph convolutional networks for learning with few clean and many noisy labels

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum, Cordelia Schmid
ECCV 2020poster

In this work we consider the problem of learning a classifier from noisy labels when a few clean labeled examples are given. The structure of clean and noisy data is modeled by a graph per class and Graph Convolutional Networks (GCN) are used to predict class relevance of noisy examples. For each cl…

Cited by 25Source ↗PDF ↗code ↗Scholar ↗
2018

Fast Spectral Ranking for Similarity Search

Ahmet Iscen, Yannis Avrithis, Giorgos Tolias, Teddy Furon, Ondřej Chum
CVPR 2018poster

Despite the success of deep learning on representing images for particular object retrieval, recent studies show that the learned representations still lie on manifolds in a high dimensional space. This makes the Euclidean nearest neighbor search biased for this task. Exploring the manifolds online…

Cited by 66Source ↗PDF ↗Scholar ↗
2018

Mining on Manifolds: Metric Learning Without Labels

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum
CVPR 2018poster

In this work we present a novel unsupervised framework for hard training example mining. The only input to the method is a collection of images relevant to the target application and a meaningful initial representation, provided e.g. by pre-trained CNN. Positive examples are distant points on a sing…

Cited by 145Source ↗PDF ↗code ↗Scholar ↗
2018

Revisiting Oxford and Paris: Large-Scale Image Retrieval Benchmarking

Filip Radenović, Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Ondřej Chum
CVPR 2018poster

In this paper we address issues with image retrieval benchmarking on standard and popular Oxford 5k and Paris 6k datasets. In particular, annotation errors, the size of the dataset, and the level of challenge are addressed: new annotation for both datasets is created with an extra attention to the r…

Cited by 542Source ↗PDF ↗Scholar ↗
2017

Efficient Diffusion on Region Manifolds: Recovering Small Objects With Compact CNN Representations

Ahmet Iscen, Giorgos Tolias, Yannis Avrithis, Teddy Furon, Ondrej Chum
CVPR 2017poster

Query expansion is a popular method to improve the quality of image retrieval with both conventional and CNN representations. It has been so far limited to global image similarity. This work focuses on diffusion, a mechanism that captures the image manifold in the feature space. An efficient off-lin…

Cited by 233PDF ↗code ↗Scholar ↗
2015

Web-Scale Image Clustering Revisited

Yannis Avrithis, Yannis Kalantidis, Evangelos Anagnostopoulos, Ioannis Z. Emiris
ICCV 2015oral

Large scale duplicate detection, clustering and mining of documents or images has been conventionally treated with seed detection via hashing, followed by seed growing heuristics using fast search. Principled clustering methods, especially kernelized and spectral ones, have higher complexity and are…

Cited by 47PDF ↗code ↗Scholar ↗