Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation

(1) , (2) , (1) , (1)
1
2

Abstract

Deep learning-based image understanding techniques require a large number of labeled images for training. Few-shot semantic segmentation, on the contrary, aims at generalizing the segmentation ability of the model to new categories given only a few labeled samples. To tackle this problem, we propose a novel prototypical network (MAPnet) with multiscale feature attention. To fully exploit the representative features of target classes, we firstly extract rich contextual information of labeled support images via a multiscale feature enhancement module. The learned prototypes from support features provide further semantic guidance on the query image. Then we adaptively integrate multiple similarity-guided probability maps by attention mechanism, yielding an optimal pixel-wise prediction. Furthermore, the proposed method was validated on the PASCAL-5 i dataset in terms of 1-way N-shot evaluation. We also test the model with weak annotations, including scribble and bounding box annotations. Both the qualitative and quantitative results demonstrate the advantages of our approach over other state-of-the-art methods.
Fichier principal
Vignette du fichier
2020_yifei_icpr_1.pdf (5.15 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02977830 , version 1 (26-10-2020)

Identifiers

  • HAL Id : hal-02977830 , version 1

Cite

Yifei Zhang, Désiré Sidibé, Olivier Morel, Fabrice Meriaudeau. Multiscale Attention-Based Prototypical Network For Few-Shot Semantic Segmentation. 25th International Conference on Pattern Recognition (ICPR 2020), Jan 2021, Milan, Italy. pp.7372--7378. ⟨hal-02977830⟩
302 View
276 Download

Share

Gmail Facebook Twitter LinkedIn More