Publications

The following is a list of my publications. I currently work on the application of representation learning methods to earth observation and computer vision with tools such as Optimal Transport. The complete list of publications can be found on my Google Scholar account.

Other interests include developer tools and programming language implementations. In this context, I regularly contribute to open-source projects related to this topic such as Pluto.jl or Reactant.jl.

Contributions to Representation Learning in Computer Vision and Remote Sensing

13/12/2024  ·  1 minute  ·  Paul Berg
Manuscript I successfully defended my thesis on the 13/12/2024 after a bit more than three years 🎓🎉 Over these three years, I explored different problems ranging from optimal transport based self-supervised learning to applications of self-supervised learning to remote sensing tasks.

Horospherical Learning with Smart Prototypes

25/11/2024  ·  2 minutes  ·  Paul Berg, Björn Michele, Minh-Tan Pham, Laetitia Chapel, Nicolas Courty
Published as an oral at BMVC 2024. Paper Code Hyperbolic spaces have emerged as an effective manifold to learn representations due to their ability to efficiently represent hierarchical data structures, with little distortion, even for low-dimensional embeddings. In the chosen hyperbolic model, such as the Poincaré ball, classification is usually conducted by leveraging a signed distance function …

Box for Mask and Mask for Box: weak losses for multi-task partially supervised learning

27/11/2024  ·  1 minute  ·  Hoang-Ân Lê, Paul Berg, Minh-Tan Pham
Published as a poster at BMVC 2024. Paper Code Object detection and semantic segmentation are both scene understanding tasks yet they differ in data structure and information level. Object detection requires box coordinates for object instances while semantic segmentation requires pixel-wise class labels. Making use of one task’s information to train the other would be beneficial for …

Multimodal Supervised Contrastive Learning in Remote Sensing Downstream Tasks

15/04/2024  ·  1 minute  ·  Paul Berg, Baki Uzun, Minh-Tan Pham, Nicolas Courty
Based on the previous article, we generalize our multi-modal contrastive learning framework to the supervised setting.

Joint multi-modal Self-Supervised pre-training in Remote Sensing: Application to Methane Source Classification

19/06/2023  ·  1 minute  ·  Paul Berg, Minh-Tan Pham, Nicolas Courty
In the task of multi-modal classification, we introduce a contrastive learning framework which is based on the regular contrastive learning from computer vision.

Spherical Sliced Wasserstein

01/05/2023  ·  Clément Bonet, Paul Berg, Nicolas Courty, Lucas Drumetz, François Septier, Minh-Tan Pham

Automatic part segmentation of facial anatomies using geometric deep learning toward a computer-aided facial rehabilitation

01/03/2023  ·  Duc-Phong Nguyen, Paul Berg, Bilel Debbabi, Tan-Nhu Nguyen, Vi-Do Tran, Ho-Quang Nguyen, Stéphanie Dakpé, Tien-Tuan Dao

Self-Supervised Learning for Scene Classification in Remote Sensing: Current State of the Art and Perspectives

17/08/2022  ·  1 minute  ·  Paul Berg, Minh-Tan Pham, Nicolas Courty
We review the current state of the art in self-supervised pre-training for computer vision and remote sensing. Peculiarities in remote sensing data often require the development of bespoke methods.

Weakly Supervised Detection of Marine Animals in High Resolution Aerial Images

12/01/2022  ·  2 minutes  ·  Paul Berg, Deise Santana Maia, Minh-Tan Pham, Sébastien Lefèvre
Paper Code Human activities in the sea, such as intensive fishing and exploitation of offshore wind farms, may impact negatively on the marine mega fauna. As an attempt to control such impacts, surveying, and tracking of marine animals are often performed on the sites where those activities take place. Nowadays, thank to high resolution cameras and to the development of machine learning …