发表机构
Hangzhou International Innovation Institute of Beihang University; Beijing University of Posts and Telecommunications; Shenzhen Campus of Sun Yat-sen University（北京航空航天大学杭州国际创新研究院; 北京邮电大学; 中山大学深圳校区）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对小目标检测中视觉线索不足、频域噪声与标签歧义被忽视的问题，提出DyFrDet检测器，通过DyFrFPN与LDM模块实现精确检测，在多基准上达SOTA性能。
AI 中文摘要
尽管过去几十年取得了显著进展，但精确识别小目标仍然极具挑战性，因为它们的视觉线索不足。以往研究通常尝试构建小目标的判别性表示，但广泛存在的频域噪声和标签歧义性被严重忽视，这极大阻碍了精确定位。为解决这些问题，本文提出一种名为DyFrDet的新型小目标检测（SOD）检测器，可通过动态抑制频域中的背景干扰来精确定位小目标。具体而言，本文提出动态频率感知特征金字塔网络（DyFrFPN），以自适应抑制低频冗余和过多高频噪声；该网络将分层特征转换为频域表示，并引入动态频带预测器（DBP）保留用于小目标识别的判别性成分。此外，本文提出新型标签歧义消解模块（LDM），利用概率分布显式建模并缓解目标标签的固有歧义性，从而有效提升低分辨率小目标的定位精度。大量实验表明，DyFrDet在多个基准上实现了最先进的性能，证明其在各种具有挑战性场景中的有效性和鲁棒性。本文代码可在指定URL获取。
英文摘要
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.
Comments10 pages, 4 figures, 7tabs
