D\'etection de petites cibles par apprentissage profond et crit\`ere a contrario
Alina Ciocarlan, Sylvie Le Hegarat-Mascle, Sidonie Lefebvre, Clara, Barbanson

TL;DR
This paper improves small target detection in noisy environments by enhancing deep learning models with attention mechanisms and applying a contrario methods to reduce false alarms due to limited annotated data.
Contribution
It introduces a channel attention module into TransUnet and combines it with a contrario techniques to improve detection accuracy with scarce annotated data.
Findings
Significant performance improvement with channel attention in TransUnet.
Effective reduction of false alarms using a contrario methods.
Enhanced detection accuracy in low-contrast, noisy environments.
Abstract
Small target detection is an essential yet challenging task in defense applications, since differentiating low-contrast targets from natural textured and noisy environment remains difficult. To better take into account the contextual information, we propose to explore deep learning approaches based on attention mechanisms. Specifically, we propose a customized version of TransUnet including channel attention, which has shown a significant improvement in performance. Moreover, the lack of annotated data induces weak detection precision, leading to many false alarms. We thus explore a contrario methods in order to select meaningful potential targets detected by a weak deep learning training. -- La d\'etection de petites cibles est une probl\'ematique d\'elicate mais essentielle dans le domaine de la d\'efense, notamment lorsqu'il s'agit de diff\'erencier ces cibles d'un fond bruit\'e…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsRadiation Detection and Scintillator Technologies · Nuclear Physics and Applications · Infrared Target Detection Methodologies
MethodsNetwork On Network
