• Home
  • Search
  • Few-Shot Object Detection with Local Feature Enhancement and Feature Interrelation
  • Cite Icon2
  • https://doi.org/10.3390/electronics12194036Copy DOI Icon

Few-Shot Object Detection with Local Feature Enhancement and Feature Interrelation

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Few-shot object detection (FSOD) aims at designing models that can accurately detect targets of novel classes in a scarce data regime. Existing research has improved detection performance with meta-learning-based models. However, existing methods continue to exhibit certain imperfections: (1) Only the interacting global features of query and support images lead to ignoring local critical features in the imprecise localization of objects from new categories. (2) Convolutional neural networks (CNNs) encounter difficulty in learning diverse pose features from exceedingly limited labeled samples of unseen classes. (3) Local context information is not fully utilized in a global attention mechanism, which means the attention modules need to be improved. As a result, the detection performance of novel-class objects is compromised. To overcome these challenges, a few-shot object detection network is proposed with a local feature enhancement module and an intrinsic feature transformation module. In this paper, a local feature enhancement module (LFEM) is designed to raise the importance of intrinsic features of the novel-class samples. In addition, an Intrinsic Feature Transform Module (IFTM) is explored to enhance the feature representation of novel-class samples, which enriches the feature space of novel classes. Finally, a more effective cross-attention module, called Global Cross-Attention Network (GCAN), which fully aggregates local and global context information between query and support images, is proposed in this paper. The crucial features of novel-class objects are extracted effectively by our model before the feature fusion between query images and support images. Our proposed method increases, on average, the detection performance by 0.93 (nAP) in comparison with previous models on the PASCAL VOC FSOD benchmark dataset. Extensive experiments demonstrate the effectiveness of our modules under various experimental settings.

Loading PDF

Similar Papers
  • PDF
  • Research Article

HDAM: Heuristic Difference Attention Module for Convolutional Neural Networks

  • Jan 01, 2022
  • Journal on Internet of Things
  • Yu Xue +1
  • Research Article
  • Citations12

A scene segmentation algorithm combining the body and the edge of the object

  • Dec 01, 2021
  • Information Processing & Management
  • Xianfeng Ou +4
  • Conference Article
  • Citations1

Document-Level Joint Biomedical Event Extraction Model Using Hypergraph Convolutional Networks

  • Oct 09, 2022
  • Jinghao Gong +3
  • Book Chapter
  • Citations194

Keyword Extraction Using Support Vector Machine

  • Jan 01, 2006
  • Kuo Zhang +3
  • Research Article

Temporal consistency-aware network for renal artery segmentation in X-ray angiography.

  • Aug 02, 2025
  • International journal of computer assisted radiology and surgery
  • Botao Yang +10
  • Conference Article
  • Citations53

Collaboratively Improving Topic Discovery and Word Embeddings by Coordinating Global and Local Contexts

  • Aug 04, 2017
  • Guangxu Xun +3
  • Research Article
  • Citations1

Context‐based robust face detection algorithm for surveillance cameras

  • Sep 18, 2012
  • IEEJ Transactions on Electrical and Electronic Engineering
  • Shotaro Miwa +2
  • Research Article
  • Citations2

Combined query embroidery image retrieval based on enhanced CNN and blend transformer

  • Nov 11, 2024
  • Scientific Reports
  • Xinzhen Zhuo +3
  • Research Article
  • Citations9

DE-UFormer: U-shaped dual encoder architectures for brain tumor segmentation

  • Sep 26, 2023
  • Physics in Medicine & Biology
  • Yan Dong +4
  • Research Article
  • Citations27

GC–HGNN: A global-context supported hypergraph neural network for enhancing session-based recommendation

  • Mar 01, 2022
  • Electronic Commerce Research and Applications
  • Dunlu Peng +1
  • Research Article

Strategic adaptations to deceptive actions in sports: The anticipation-response-inhibition-accuracy trade-off.

  • Jul 01, 2026
  • Psychology of sport and exercise
  • Carolin Wickemeyer +2
  • Conference Article
  • Citations3

Deep Learning Model with GA-based Visual Feature Selection and Context Integration

  • Jun 28, 2021
  • Ranju Mandal +3
  • Research Article
  • Citations32

LSRFormer: Efficient Transformer Supply Convolutional Neural Networks With Global Information for Aerial Image Segmentation

  • Jan 01, 2024
  • IEEE Transactions on Geoscience and Remote Sensing
  • Renhe Zhang +2
  • Research Article
  • Citations6

BIG-FUSION: Brain-Inspired Global-Local Context Fusion Framework for Multimodal Emotion Recognition in Conversations

  • Apr 11, 2025
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Yusong Wang +8
  • Research Article
  • Citations1

A FLEXIBLE SUB-BLOCK IN REGION BASED IMAGE RETRIEVAL BASED ON TRANSITION REGION

  • Feb 28, 2018
  • Jurnal Ilmu Komputer dan Informasi
  • Ahmad Wahyu Rosyadi +3
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.