Open Access

ARTICLE

Implicit Feature Contrastive Learning for Few-Shot Object Detection

Gang Li^1,#, Zheng Zhou^1,#, Yang Zhang^2,*, Chuanyun Xu², Zihan Ruan¹, Pengfei Lv¹, Ru Wang¹, Xinyu Fan¹, Wei Tan¹

1 School of Artificial Intelligence, Chongqing University of Technology, Chongqing, 401331, China
2 School of Computer and Information Science, Chongqing Normal University, Chongqing, 401331, China

* Corresponding Author: Yang Zhang. Email:
# These authors contributed equally to this work

(This article belongs to the Special Issue: Research on Deep Learning-based Object Detection and Its Derivative Key Technologies)

Computers, Materials & Continua 2025, 84(1), 1615-1632. https://doi.org/10.32604/cmc.2025.063109

Received 05 January 2025; Accepted 29 April 2025; Issue published 09 June 2025

Abstract

Although conventional object detection methods achieve high accuracy through extensively annotated datasets, acquiring such large-scale labeled data remains challenging and cost-prohibitive in numerous real-world applications. Few-shot object detection presents a new research idea that aims to localize and classify objects in images using only limited annotated examples. However, the inherent challenge in few-shot object detection lies in the insufficient sample diversity to fully characterize the sample feature distribution, which consequently impacts model performance. Inspired by contrastive learning principles, we propose an Implicit Feature Contrastive Learning (IFCL) module to address this limitation and augment feature diversity for more robust representational learning. This module generates augmented support sample features in a mixed feature space and implicitly contrasts them with query Region of Interest (RoI) features. This approach facilitates more comprehensive learning of both intra-class feature similarity and inter-class feature diversity, thereby enhancing the model’s object classification and localization capabilities. Extensive experiments on PASCAL VOC show that our method achieves a respective improvement of 3.2%, 1.8%, and 2.3% on 10-shot of three Novel Sets compared to the baseline model FPD.

---

Keywords

---