From Spatial to Spectral: An Efficient, Frequency-Guided Feature Representation Learner for Small Object Detection

arXiv:2606.23825v1 Announce Type: cross Abstract: Efficient small object detection is bottlenecked by the inherent feature scarcity of tiny targets, which is further aggravated by operations of spatial-domain detectors that indiscriminately discard critical high-frequency details. Recovering these fragile cues within the spatial domain is notoriously difficult, as it often requires computationally expensive architectural upscaling that inadvertently amplifies background noise. To bridge this gap, we propose a paradigm extbf{shift from spatial to spectral} feature processing, introducing a holistic solution with the following novelty: (1) A versatile extbf{Frequency-Guided Feature Representation framework} that generalizes across diverse detector architectures (both CNN and Transformer-based), offering a robust alternative to spatial-only feature extraction; (2) The unified extbf{Decompose--Enhance--Reconstruct (DER)} operator, instantiated via three extbf{lightweight, plug-and-play} modules -- Wavelet-Difference Gate (WDG), Log-Gabor Enhancer (LGE), and Frequency-Driven Head (FDHead) -- to systematically inject frequency-aware modulation into the backbone, neck, and head. This mechanism decouples feature modeling from resolution reduction, capturing discriminative high-frequency components to enable accurate localization with significantly reduced parameter redundancy; (3) Extensive validation on multi-domain benchmarks (VisDrone2019, UAVDT, TinyPerson, DOTAv1) demonstrating consistent gains. Notably, our proposed extbf{DERNet} series outperforms YOLOv11 models under the same scale while requiring extbf{only 1/6 of the parameters}, backed by rigorous spectral diagnostics and error decomposition analysis.

Source: arXiv cs.AI | 2026-06-24