| Title: |
Optimal transport unlocks end-to-end learning for single-molecule localization |
| Authors: |
Seailles, Romain; Masson, Jean-Baptiste; Ponce, Jean; Mairal, Julien |
| Contributors: |
Département d'informatique - ENS-PSL (DI-ENS); École normale supérieure - Paris (ENS-PSL); Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS); Models of visual object recognition and scene understanding (WILLOW); Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-École normale supérieure - Paris (ENS-PSL); Université Paris Sciences et Lettres (PSL)-Université Paris Sciences et Lettres (PSL)-Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Centre Inria de Paris; Institut National de Recherche en Informatique et en Automatique (Inria); Université Grenoble Alpes (UGA); Décision et processus Bayesiens - Decision and Bayesian Computation; Institut Pasteur Paris (IP)-Centre National de la Recherche Scientifique (CNRS)-Université Paris Cité (UPCité); Approches expérimentales et numériques pour explorer le cerveau des insectes (EPIMETHEE); Institut Pasteur Paris (IP)-Centre National de la Recherche Scientifique (CNRS)-Centre Inria de Paris; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria); Center for Data Science NYU (CDS); New York University New York (NYU); NYU System (NYU)-NYU System (NYU); Apprentissage de modèles à partir de données massives (Thoth); Centre Inria de l'Université Grenoble Alpes; Institut National de Recherche en Informatique et en Automatique (Inria)-Institut National de Recherche en Informatique et en Automatique (Inria)-Laboratoire Jean Kuntzmann (LJK); Institut National de Recherche en Informatique et en Automatique (Inria)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP); Université Grenoble Alpes (UGA)-Centre National de la Recherche Scientifique (CNRS)-Université Grenoble Alpes (UGA)-Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP); This work was supported by the French government through the ”France 2030” program, in particular by the PR AI RIE-PSAI project (ref. ANR-23-IACL-0008). Julien Mairal was also supported by ERC grant number 101087696 (APHELEIA project), and Jean Ponce was also supported in part by the Louis Vuitton/ENS chair in artificial intelligence and a Global Distinguished Professorship at the Courant Institute of Mathematical Sciences and the Center for Data Science at New York University. We received access to the computational resources of IDRIS from GENCI (ref. AD010616282); ANR-23-IACL-0008,PR AI RIE-PSAI,PR AI RIE-PSAI - Paris School of Artificial Intelligence(2023); European Project: 101087696,ERC-2022-COG,ERC-2022-COG,APHELEIA(2023) |
| Source: |
ICLR 2026: The Fourteenth International Conference on Learning Representations ; https://hal.science/hal-05397581 ; ICLR 2026: The Fourteenth International Conference on Learning Representations, Apr 2026, Rio de Janeiro, Brazil. 2026 |
| Publisher Information: |
CCSD |
| Publication Year: |
2026 |
| Subject Terms: |
optimal transport; end-to-end; deep learning; Super resolution microscopy; SMLM; Single-molecule localization microscopy; [INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]; [INFO.INFO-LG]Computer Science [cs]/Machine Learning [cs.LG] |
| Subject Geographic: |
Rio de Janeiro; Brazil |
| Description: |
International audience ; Single-molecule localization microscopy (SMLM) allows reconstructing biology-relevant structures beyond the diffraction limit by detecting and localizing individual fluorophores --- fluorescent molecules stained onto the observed specimen --- over time to reconstruct super-resolved images.Currently, efficient SMLM requires non-overlapping emitting fluorophores, leading to long acquisition times that hinders live-cell imaging.Recent deep-learning approaches can handle denser emissions, but they rely on variants of non-maximum suppression (NMS) layers, which are unfortunately non-differentiable and may discard true positives with their local fusion strategy.In this presentation, we reformulate the SMLM training objective as a set-matching problem, deriving an optimal-transport loss that eliminates the need for NMS during inference and enables end-to-end training.Additionally, we propose an iterative neural network that integrates knowledge of the microscope's optical system inside our model.Experiments on synthetic benchmarks and real biological data show that both our new loss function and architecture surpass the state of the art at moderate and high emitter densities.Code is available at https://github.com/RSLLES/SHOT. |
| Document Type: |
conference object |
| Language: |
English |
| Relation: |
info:eu-repo/semantics/altIdentifier/arxiv/2512.10683; info:eu-repo/grantAgreement//101087696/EU/Reconciling Classical and Modern (Deep) Machine Learning for Real-World Applications/APHELEIA; ARXIV: 2512.10683 |
| Availability: |
https://hal.science/hal-05397581; https://hal.science/hal-05397581v2/document; https://hal.science/hal-05397581v2/file/main.pdf |
| Rights: |
https://creativecommons.org/licenses/by-nc/4.0/ ; info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.25440F46 |
| Database: |
BASE |