DyFrDet: Towards Accurate Small Object Detection via Dynamic Frequency Suppression with Label Disambiguation
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern RecognitionArtificial Intelligence
AI summaryⓘ
The authors address the challenge of detecting small objects, which is hard because small objects don't have many clear visual details. They developed a new method called DyFrDet that works by filtering out distracting background noise in frequency space to better find small objects. Their approach includes a special network (DyFrFPN) that adapts to remove unwanted frequency information and a module (LDM) that deals with unclear labeling of objects to improve detection accuracy. Experiments show their method performs very well on different test sets.
small object detectionfrequency domainfeature pyramid networknoise suppressionlabel ambiguityfrequency representationobject localizationprobabilistic modelingcomputer vision
Authors
Zihan Yang, Yang Guo, Hongxing Zhang, Dan Lu, Siyuan Yao
Abstract
Despite the remarkable progress over the past decades, accurately identifying small objects remains challenging because of their insufficient visual cues. Previous works typically attempt to construct discriminative representation of the small objects. However, the wide range frequency domain noises and label ambiguities have been greatly overlooked, which significantly hinders the accurate localization. To address these issues, we propose a novel small object detection (SOD) detector termed DyFrDet, which is able to precisely localize the small object by dynamically suppressing the background distractions in frequency domain. Specifically, we propose a Dynamic Frequency-aware Feature Pyramid Network (DyFrFPN) to adaptively suppress low-frequency redundancy and excessive high-frequency noises. The DyFrFPN transforms the hierarchical features into frequency domain representation, and introduces a Dynamic Band Predictor (DBP) to preserve the discriminative components for small object identification. Afterwards, we present a novel Label Disambiguation Module (LDM), which leverages probabilistic distributions to explicitly model and alleviate the inherent ambiguity of target labels, yielding efficient improvement in localization precision of the small objects with low-resolution. Extensive experiments demonstrate that DyFrDet achieves state-of-the-art performance across multiple benchmarks, indicating its effectiveness and robustness in various challenging scenarios. Our code is available at https://github.com/ManOfStory/DyFrDet.