YOLO-DS: Fine-Grained Feature Decoupling via Dual-Statistic Synergy Operator for Object Detection

• URL: http://arxiv.org/abs/2601.18172v1
• Date: Mon, 26 Jan 2026 05:50:32 GMT
• Title: YOLO-DS: Fine-Grained Feature Decoupling via Dual-Statistic Synergy Operator for Object Detection
• Authors: Lin Huang, Yujuan Tan, Weisheng Li, Shitai Shan, Liu Liu, Bo Liu, Linlin Shen, Jing Yu, Yue Niu,
• Abstract summary: We propose YOLO-DS, a framework built around a novel Dual-Statistic Synergy Operator (DSO)<n>YOLO-DS decouples object features by jointly modeling the channel-wise mean and the peak-to-mean difference.<n>On the MS-COCO benchmark, YOLO-DS consistently outperforms YOLOv8 across five model scales.
• Score: 55.58092342624062
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: One-stage object detection, particularly the YOLO series, strikes a favorable balance between accuracy and efficiency. However, existing YOLO detectors lack explicit modeling of heterogeneous object responses within shared feature channels, which limits further performance gains. To address this, we propose YOLO-DS, a framework built around a novel Dual-Statistic Synergy Operator (DSO). The DSO decouples object features by jointly modeling the channel-wise mean and the peak-to-mean difference. Building upon the DSO, we design two lightweight gating modules: the Dual-Statistic Synergy Gating (DSG) module for adaptive channel-wise feature selection, and the Multi-Path Segmented Gating (MSG) module for depth-wise feature weighting. On the MS-COCO benchmark, YOLO-DS consistently outperforms YOLOv8 across five model scales (N, S, M, L, X), achieving AP gains of 1.1% to 1.7% with only a minimal increase in inference latency. Extensive visualization, ablation, and comparative studies validate the effectiveness of our approach, demonstrating its superior capability in discriminating heterogeneous objects with high efficiency.

Related papers

• YOLOA: Real-Time Affordance Detection via LLM Adapter [96.61111291833544]
  Affordance detection aims to jointly address the fundamental "what-where-how" challenge in embodied AI.<n>We introduce YOLO Affordance (YOLOA), a real-time affordance detection model that jointly handles object detection and affordance learning.<n>Experiments on our relabeled ADG-Det and IIT-Heat benchmarks demonstrate that YOLOA achieves state-of-the-art accuracy while maintaining real-time performance.
  arXiv  Detail & Related papers  (2025-12-03T03:53:31Z)
• YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perception [58.06752127687312]
  We propose YOLOv13, an accurate and lightweight object detector.<n>We propose a Hypergraph-based Adaptive Correlation Enhancement (HyperACE) mechanism.<n>We also propose a Full-Pipeline Aggregation-and-Distribution (FullPAD) paradigm.
  arXiv  Detail & Related papers  (2025-06-21T15:15:03Z)
• YOLO-SPCI: Enhancing Remote Sensing Object Detection via Selective-Perspective-Class Integration [1.2815904071470707]
  YOLO-S PCI is an attention-enhanced detection framework that introduces a lightweight Selective-Perspective-Class Integration module.<n>YOLO-S PCI achieves superior performance compared to state-of-the-art detectors.
  arXiv  Detail & Related papers  (2025-05-27T16:00:34Z)
• MASF-YOLO: An Improved YOLOv11 Network for Small Object Detection on Drone View [0.0]
  We propose a novel object detection network Multi-scale Context Aggregation and Scale-adaptive Fusion YOLO (MASF-YOLO)<n>To tackle the difficulty of detecting small objects in UAV images, we design a Multi-scale Feature Aggregation Module (MFAM), which significantly improves the detection accuracy of small objects.<n>Thirdly, we introduce a Dimension-Aware Selective Integration Module (DASI), which further enhances multi-scale feature fusion capabilities.
  arXiv  Detail & Related papers  (2025-04-25T07:43:33Z)
• YOLO-PRO: Enhancing Instance-Specific Object Detection with Full-Channel Global Self-Attention [38.97680747773625]
  This paper addresses the inherent limitations of conventional bottleneck structures in object detection frameworks.<n>It proposes two novel modules: the Instance-Specific Bottleneck with full-channel global self-attention (ISB) and the Instance-Specific Asymmetric Decoupled Head (ISADH)<n> experiments on the MS-COCO benchmark demonstrate that the coordinated deployment of ISB and ISADH in the YOLO-PRO framework achieves state-of-the-art performance across all computational scales.
  arXiv  Detail & Related papers  (2025-03-04T07:17:02Z)
• YOLOv10: Real-Time End-to-End Object Detection [68.28699631793967]
  YOLOs have emerged as the predominant paradigm in the field of real-time object detection. The reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs. We introduce the holistic efficiency-accuracy driven model design strategy for YOLOs.
  arXiv  Detail & Related papers  (2024-05-23T11:44:29Z)
• YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection [63.36722419180875]
  We provide an efficient and performant object detector, termed YOLO-MS.<n>We train our YOLO-MS on the MS COCO dataset from scratch without relying on any other large-scale datasets.<n>Our work can also serve as a plug-and-play module for other YOLO models.
  arXiv  Detail & Related papers  (2023-08-10T10:12:27Z)
• Towards End-to-end Semi-supervised Learning for One-stage Object Detection [88.56917845580594]
  This paper focuses on the semi-supervised learning for the advanced and popular one-stage detection network YOLOv5. We propose a novel teacher-student learning recipe called OneTeacher with two innovative designs, namely Multi-view Pseudo-label Refinement (MPR) and Decoupled Semi-supervised Optimization (DSO) In particular, MPR improves the quality of pseudo-labels via augmented-view refinement and global-view filtering, and DSO handles the joint optimization conflicts via structure tweaks and task-specific pseudo-labeling.
  arXiv  Detail & Related papers  (2023-02-22T11:35:40Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.