YOLO-PRO: Enhancing Instance-Specific Object Detection with Full-Channel Global Self-Attention

• URL: http://arxiv.org/abs/2503.02348v1
• Date: Tue, 04 Mar 2025 07:17:02 GMT
• Title: YOLO-PRO: Enhancing Instance-Specific Object Detection with Full-Channel Global Self-Attention
• Authors: Lin Huang, Yujuan Tan, Weisheng Li, Shitai Shan, Linlin Shen, Jing Yu,
• Abstract summary: 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.
• Score: 37.89051124090947
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: This paper addresses the inherent limitations of conventional bottleneck structures (diminished instance discriminability due to overemphasis on batch statistics) and decoupled heads (computational redundancy) in object detection frameworks by proposing two novel modules: the Instance-Specific Bottleneck with full-channel global self-attention (ISB) and the Instance-Specific Asymmetric Decoupled Head (ISADH). The ISB module innovatively reconstructs feature maps to establish an efficient full-channel global attention mechanism through synergistic fusion of batch-statistical and instance-specific features. Complementing this, the ISADH module pioneers an asymmetric decoupled architecture enabling hierarchical multi-dimensional feature integration via dual-stream batch-instance representation fusion. Extensive 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. Specifically, YOLO-PRO surpasses YOLOv8 by 1.0-1.6% AP (N/S/M/L/X scales) and outperforms YOLO11 by 0.1-0.5% AP in critical M/L/X groups, while maintaining competitive computational efficiency. This work provides practical insights for developing high-precision detectors deployable on edge devices.

Related papers

• Interpreting CLIP with Hierarchical Sparse Autoencoders [8.692675181549117]
  Matryoshka SAE (MSAE) learns hierarchical representations at multiple granularities simultaneously. MSAE establishes a new state-of-the-art frontier between reconstruction quality and sparsity for CLIP.
  arXiv  Detail & Related papers  (2025-02-27T22:39:13Z)
• FedOC: Optimizing Global Prototypes with Orthogonality Constraints for Enhancing Embeddings Separation in Heterogeneous Federated Learning [31.93057335216804]
  Federated Learning (FL) has emerged as an essential framework for distributed machine learning, especially with its potential for privacy-preserving data processing.<n>Existing FL frameworks struggle to address statistical and model heterogeneity, which impacts model performance.<n>This paper introduces novel Heterogeneous Federated Learning (HtFL) algorithm designed to improve global prototype separation through Fedity constraints.
  arXiv  Detail & Related papers  (2025-02-22T07:02:51Z)
• YOLOv12: A Breakdown of the Key Architectural Features [0.5639904484784127]
  YOLOv12 is a significant advancement in single-stage, real-time object detection. It incorporates an optimised backbone (R-ELAN), 7x7 separable convolutions, and FlashAttention-driven area-based attention. It offers scalable solutions for both latency-sensitive and high-accuracy applications.
  arXiv  Detail & Related papers  (2025-02-20T17:08:43Z)
• SOOD++: Leveraging Unlabeled Data to Boost Oriented Object Detection [59.868772767818975]
  We propose a simple yet effective Semi-supervised Oriented Object Detection method termed SOOD++. Specifically, we observe that objects from aerial images are usually arbitrary orientations, small scales, and aggregation. Extensive experiments conducted on various multi-oriented object datasets under various labeled settings demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2024-07-01T07:03:51Z)
• Stragglers-Aware Low-Latency Synchronous Federated Learning via Layer-Wise Model Updates [71.81037644563217]
  Synchronous federated learning (FL) is a popular paradigm for collaborative edge learning. As some of the devices may have limited computational resources and varying availability, FL latency is highly sensitive to stragglers. We propose straggler-aware layer-wise federated learning (SALF) that leverages the optimization procedure of NNs via backpropagation to update the global model in a layer-wise fashion.
  arXiv  Detail & Related papers  (2024-03-27T09:14:36Z)
• ASF-YOLO: A Novel YOLO Model with Attentional Scale Sequence Fusion for Cell Instance Segmentation [6.502259209532815]
  We propose an Attentional Scale Sequence Fusion based You Only Look Once (YOLO) framework (ASF-YOLO) It combines spatial and scale features for accurate and fast cell instance segmentation. It achieves a box mAP of 0.91, mask mAP of 0.887, and an inference speed of 47.3 FPS on the 2018 Data Science Bowl dataset.
  arXiv  Detail & Related papers  (2023-12-11T15:47:12Z)
• Omni Aggregation Networks for Lightweight Image Super-Resolution [42.252518645833696]
  This work proposes two enhanced components under a new Omni-SR architecture. First, an Omni Self-Attention (OSA) block is proposed based on dense interaction principle. Second, a multi-scale interaction scheme is proposed to mitigate sub-optimal ERF.
  arXiv  Detail & Related papers  (2023-04-20T12:05:14Z)
• USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval [115.28586222748478]
  Image-Text Retrieval (ITR) aims at searching for the target instances that are semantically relevant to the given query from the other modality. Existing approaches typically suffer from two major limitations.
  arXiv  Detail & Related papers  (2023-01-17T12:42:58Z)
• A Generic Shared Attention Mechanism for Various Backbone Neural Networks [53.36677373145012]
  Self-attention modules (SAMs) produce strongly correlated attention maps across different layers. Dense-and-Implicit Attention (DIA) shares SAMs across layers and employs a long short-term memory module. Our simple yet effective DIA can consistently enhance various network backbones.
  arXiv  Detail & Related papers  (2022-10-27T13:24:08Z)
• Joint Spatial-Temporal and Appearance Modeling with Transformer for Multiple Object Tracking [59.79252390626194]
  We propose a novel solution named TransSTAM, which leverages Transformer to model both the appearance features of each object and the spatial-temporal relationships among objects. The proposed method is evaluated on multiple public benchmarks including MOT16, MOT17, and MOT20, and it achieves a clear performance improvement in both IDF1 and HOTA.
  arXiv  Detail & Related papers  (2022-05-31T01:19:18Z)

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.