Frequency Introduced Cascade Feature Fusion Network via Knowledge Distillation for Infrared Small Target Detection
- 10 November 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Geoscience and Remote Sensing
- Vol. 63 (01962892) , 1-17
Abstract
Infrared small target detection (IRSTD) plays a crucial role in numerous applications and has benefited significantly from recent advances in deep learning. However, existing methods often face two major challenges: (1) difficulty in detecting non-salient small targets embedded in complex backgrounds, and (2) substantial computational costs during inference, which limit practical deployment. To address these issues, we propose the Frequency Introduced Cascade Feature Fusion Network (FICFFNet), which leverages high-frequency information from infrared images to enhance target saliency, and incorporates a knowledge distillation (KD) framework to balance detection accuracy and efficiency. Specifically, infrared and frequency features are jointly extracted and adaptively fused, enabling effective integration of spatial and frequency-domain cues and improving localization of tiny objects with local temperature variations. Adjacent-level features are further aggregated to combine low-level spatial details with high-level contextual semantics, ensuring robust multi-scale prediction. A lightweight student network is constructed by simplifying the architecture, while multiple distillation paths transfer crucial knowledge from the dual-stream features and prediction maps to the single-stream representation. We also construct two infrared tiny bird detection datasets by collecting and annotating infrared images from transformer substations. Extensive experiments on both self-built and public datasets demonstrate that FICFFNet achieves superior detection performance while maintaining high computational efficiency. Our code will be made public at: github.com/HHUyxt/IRTBD.Keywords
Funding Information
- Key research and development plan of Jiangsu Province (BE2020649, BE2021042)
- Natural Science Foundation of Ningxia Province (E329CC240000)
This publication has 60 references indexed in Scilit:
- Spatial-Frequency Complementary Transformer and Multi-Scale Attention Refinement for Image InpaintingJournal of Shanghai Jiaotong University (Science), 2025
- Deep learning based infrared small object segmentation: Challenges and future directionsInformation Fusion, 2025
- IRSAM: Advancing Segment Anything Model for Infrared Small Target Detection2024
- Wavelet Convolutions for Large Receptive Fields2024
- Frequency-Spatial Entanglement Learning for Camouflaged Object Detection2024
- DCANet: Dense Convolutional Attention Network for infrared small target detectionMeasurement, 2024
- MSKD: Structured knowledge distillation for efficient medical image segmentationComputers in Biology and Medicine, 2023
- RGB-T image analysis technology and application: A surveyEngineering Applications of Artificial Intelligence, 2023
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- The design of Top-Hat morphological filter and application to infrared target detectionInfrared Physics & Technology, 2006