FSDC-DETR: A Frequency-Spatial Domain Collaborative DETR for Small Object Detection
2026-07-06 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the difficulty of detecting small objects in images by creating a new detection framework that combines information from both spatial details and frequency patterns. They designed special modules to better mix and preserve important high-frequency information that usually gets lost in regular methods. This approach allows the model to gradually improve its understanding of objects across different scales, leading to more accurate detection results. Their method notably outperforms previous ones on two benchmark datasets focused on small object detection.
small object detectionfrequency domainspatial domaintransformerfeature fusionmulti-scale fusionadaptive downsamplinghigh-frequency componentsobject detectionVisDrone-DET2019
Authors
Aiwen Liu, Chengguang Zhu, Gang Wang, Dandan Zhu, Haodong Lin, Yan Wang, Huiyu Zhou, Zhiyi Pan
Abstract
Small object detection (SOD) remains a challenging task in real-world applications. Despite recent advances, existing detectors remain limited by rigid processing that entangle spatial aggregation with implicit frequency aliasing and truncation, leading to inadequate preservation of high-frequency components for SOD. To tackle these limitations, we propose a Frequency-Spatial Domain Collaborative Detection Transformer (FSDC-DETR), a novel collaborative framework that explicitly models complementary spatial and frequency representations. Specifically, we first introduce Dual-Branch Frequency-Spatial Adaptive Fusion (DBFSAF) to enhance frequency diversity and adaptively capture frequency-spatial domain discriminative representations. Building on these representations, a frequency-spatial interaction scheme is further explored within the hybrid encoder to enable progressive feature propagation to the decoder. In particular, structure-aware frequency-spatial aggregation is achieved through Shunt Frequency-Spatial Feature Fusion (SFS-FF), establishing bidirectional interaction and progressive cross-scale propagation between frequency and spatial representations for coherent discriminative modeling. Meanwhile, informative high-frequency responses are preserved during scale transitions through Frequency-Spatial Dynamic Downsampling (FSD-Down), thereby minimizing frequency degradation throughout multi-scale fusion for the precise SOD. Experimental results demonstrate that FSDC-DETR achieves state-of-the-art performance, improving AP by 6.4 on VisDrone-DET2019 and 6.6 on AITODv2, with gains of 6.8 and 6.9 AP for small objects. The code is available at github.com/nevereverinsomnia/FSDC-DETR.