mlsanityData to 14 Oct 2026

Local Foreground Selection aware Attentive Feature Reconstruction for few-shot fine-grained plant species classification

arXiv 2501.06909 ↗First posted 12 Jan 2025cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Plant species exhibit significant intra-class variation and minimal inter-class variation. To enhance classification accuracy, it is essential to reduce intra-class variation while maximizing inter-class variation. This paper addresses plant species classification using a limited number of labelled samples and introduces a novel Local Foreground Selection(LFS) attention mechanism. LFS is a straightforward module designed to generate discriminative support and query feature maps. It operates by integrating two types of attention: local attention, which captures local spatial details to enhance feature discrimination and increase inter-class differentiation, and foreground selection attention, which emphasizes the foreground plant object while mitigating background interference. By focusing on the foreground, the query and support features selectively highlight relevant feature sequences and disregard less significant background sequences, thereby reducing intra-class differences. Experimental results from three plant species datasets demonstrate the effectiveness of the proposed LFS attention mechanism and its complementary advantages over previous feature reconstruction methods.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 17 of its 24 references that are in the map. First posted on arXiv 12 Jan 2025.

Builds on

17 of 24 references.

References · 17

  1. 2017Attention Is All You Needcited by 60,361
  2. 2016Matching Networks for One Shot Learningcited by 2,255
  3. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,143
  4. 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 294
  5. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  6. 2019Revisiting Local Descriptor based Image-to-Class Measure for Few-shot Learningcited by 121
  7. 2020Few-Shot Classification with Feature Map Reconstruction Networkscited by 116
  8. 2019Low-Rank Pairwise Alignment Bilinear Network For Few-Shot Fine-Grained Image Classificationcited by 36
  9. 2020Revisiting Pose-Normalization for Fine-Grained Few-Shot Recognitioncited by 31
  10. 2020BSNet: Bi-Similarity Network for Few-shot Fine-grained Image Classificationcited by 30
  11. 2022Boosting Few-shot Fine-grained Recognition with Background Suppression and Foreground Alignmentcited by 29
  12. 2020TOAN: Target-Oriented Alignment Network for Fine-Grained Image Categorization with Few Labeled Samplescited by 13
5 more
  1. 2021NDPNet: A novel non-linear data projection network for few-shot fine-grained image classificationcited by 13
  2. 2022Bi-directional Feature Reconstruction Network for Fine-Grained Few-Shot Image Classificationcited by 12
  3. 2019Few-shot Learning for Domain-specific Fine-grained Image Classificationcited by 10
  4. 2019Meta-Reinforced Synthetic Data for One-Shot Fine-Grained Visual Recognitioncited by 9
  5. 2022Enhancing Few-shot Image Classification with Cosine Transformercited by 4

Built on by

Not cited yet.