Efficient Object Detection in Optical Remote Sensing Imagery via Attention-Based Feature Distillation - IRSTEA - Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (<b>anciennement Cemagref</b>) Accéder directement au contenu
Article Dans Une Revue IEEE Transactions on Geoscience and Remote Sensing Année : 2023

Efficient Object Detection in Optical Remote Sensing Imagery via Attention-Based Feature Distillation

Résumé

Efficient object detection methods have recently received great attention in remote sensing. Although deep convolutional networks often have excellent detection accuracy, their deployment on resource-limited edge devices is difficult. Knowledge distillation (KD) is a strategy for addressing this issue, since it makes models lightweight while maintaining accuracy. However, the existing KD methods for object detection have encountered two constraints. First, they discard potentially important background information and only distill nearby foreground regions. Second, they only rely on the global context, which limits the student detector’s ability to acquire local information from the teacher detector. To address the aforementioned challenges, we propose attention-based feature distillation (AFD), a new KD approach that distills both local and global information from the teacher detector. To enhance local distillation, we introduce a multi-instance attention mechanism that effectively distinguishes between background and foreground elements. This approach prompts the student detector to focus on the pertinent channels and pixels, as identified by the teacher detector. Local distillation lacks global information; thus, attention global distillation is proposed to reconstruct the relationship between various pixels and pass it from teacher to student detector. The performance of AFD is evaluated on two public aerial image benchmarks, and the evaluation results demonstrate that AFD in object detection can attain the performance of other state-of-the-art models while being efficient.
Fichier principal
Vignette du fichier
2310.18676v1.pdf (8.71 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04473529 , version 1 (22-07-2024)

Identifiants

Citer

Pourya Shamsolmoali, Jocelyn Chanussot, Huiyu Zhou, Yue Lu. Efficient Object Detection in Optical Remote Sensing Imagery via Attention-Based Feature Distillation. IEEE Transactions on Geoscience and Remote Sensing, 2023, 61, pp.1-12. ⟨10.1109/TGRS.2023.3328908⟩. ⟨hal-04473529⟩
10 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More