AIConfPaper
← Search

Elias Ramzi

5 accepted papers

2026

Franca: Nested Matryoshka Clustering for Scalable Visual Representation Learning

Shashanka Venkataramanan, Valentinos Pariza, Mohammadreza Salehi, Lukas Knobel, Elias Ramzi, Spyros Gidaris +2
CVPR 2026

We present Franca (pronounced Fran-ka): free one; the first fully open-source (data, code, weights) vision foundation model that matches and in many cases surpasses the performance of state-of-the-art proprietary models, e.g., DINOv2, CLIP, SigLIPv2, etc. Our approach is grounded in a transparent tr

Cited by 0Source ↗Scholar ↗
2025

LLM-wrapper: Black-Box Semantic-Aware Adaptation of Vision-Language Models for Referring Expression Comprehension

Amaia Cardiel, Eloi Zablocki, Elias Ramzi, Oriane Siméoni, Matthieu Cord
ICLR 2025poster

Vision Language Models (VLMs) have demonstrated remarkable capabilities in various open-vocabulary tasks, yet their zero-shot performance lags behind task-specific fine-tuned models, particularly in complex tasks like Referring Expression Comprehension (REC). Fine-tuning usually requires ‘white-box’…

Cited by 0Source ↗PDF ↗code ↗Scholar ↗
2023

Hybrid Energy Based Model in the Feature Space for Out-of-Distribution Detection

Marc Lafon, Elias Ramzi, Clément Rambour, Nicolas THOME
ICML 2023poster

Out-of-distribution (OOD) detection is a critical requirement for the deployment of deep neural networks. This paper introduces the HEAT model, a new post-hoc OOD detection method estimating the density of in-distribution (ID) samples using hybrid energy-based models (EBM) in the feature space of a…

Cited by 13Source ↗PDF ↗code ↗Scholar ↗
2022

Hierarchical Average Precision Training for Pertinent Image Retrieval

Elias Ramzi, Nicolas Audebert, Nicolas Thome, Clément Rambour, Xavier Bitot
ECCV 2022poster

"Image Retrieval is commonly evaluated with Average Precision (AP) or Recall@k. Yet, those metrics, are limited to binary labels and do not take into account errors’ severity. This paper introduces a new hierarchical AP training method for pertinent image retrieval (HAPPIER). HAPPIER is based on a n…

Cited by 12Source ↗PDF ↗code ↗Scholar ↗
2021

Robust and Decomposable Average Precision for Image Retrieval

Elias Ramzi, Nicolas THOME, Clément Rambour, Nicolas Audebert, Xavier Bitot
NeurIPS 2021poster

In image retrieval, standard evaluation metrics rely on score ranking, e.g. average precision (AP). In this paper, we introduce a method for robust and decomposable average precision (ROADMAP) addressing two major challenges for end-to-end training of deep neural networks with AP: non-differentiabil…

Cited by 39Source ↗PDF ↗code ↗Scholar ↗