Better (pseudo-)labels for semi-supervised instance segmentation

no code implementations • 18 Mar 2024 • François Porcher, Camille Couprie, Marc Szafraniec, Jakob Verbeek

Despite the availability of large datasets for tasks like image classification and image-text alignment, labeled data for more complex recognition tasks, such as detection and segmentation, is less abundant.

Few-Shot Learning Image Classification +3

DINOv2: Learning Robust Visual Features without Supervision

11 code implementations • 14 Apr 2023 • Maxime Oquab, Timothée Darcet, Théo Moutakanni, Huy Vo, Marc Szafraniec, Vasil Khalidov, Pierre Fernandez, Daniel Haziza, Francisco Massa, Alaaeldin El-Nouby, Mahmoud Assran, Nicolas Ballas, Wojciech Galuba, Russell Howes, Po-Yao Huang, Shang-Wen Li, Ishan Misra, Michael Rabbat, Vasu Sharma, Gabriel Synnaeve, Hu Xu, Hervé Jegou, Julien Mairal, Patrick Labatut, Armand Joulin, Piotr Bojanowski

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision.

Domain Generalization Fine-Grained Image Classification +5

Code Translation with Compiler Representations

1 code implementation • 30 Jun 2022 • Marc Szafraniec, Baptiste Roziere, Hugh Leather, Francois Charton, Patrick Labatut, Gabriel Synnaeve

Here we propose to augment code translation with IRs, specifically LLVM IR, with results on the C++, Java, Rust, and Go languages.

Code Translation Machine Translation +2

DOBF: A Deobfuscation Pre-Training Objective for Programming Languages

2 code implementations • NeurIPS 2021 • Baptiste Roziere, Marie-Anne Lachaux, Marc Szafraniec, Guillaume Lample

Recent advances in self-supervised learning have dramatically improved the state of the art on a wide variety of tasks.

Code Search Code Translation +5

Continuous Surface Embeddings

1 code implementation • NeurIPS 2020 • Natalia Neverova, David Novotny, Vasil Khalidov, Marc Szafraniec, Patrick Labatut, Andrea Vedaldi

In this work, we focus on the task of learning and representing dense correspondences in deformable object categories.

Object Pose Estimation

Putting Self-Supervised Token Embedding on the Tables

no code implementations • 28 Jul 2017 • Marc Szafraniec, Gautier Marti, Philippe Donnat

Information distribution by electronic messages is a privileged means of transmission for many businesses and individuals, often under the form of plain-text tables.