Pith. sign in

REVIEW 39 cited by

YOLOv10: Real-Time End-to-End Object Detection

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2405.14458 v2 pith:MD6D7EGB submitted 2024-05-23 cs.CV

YOLOv10: Real-Time End-to-End Object Detection

classification cs.CV
keywords yolosperformancedetectionmodelcomputationalefficiencyend-to-endlatency
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Over the past years, YOLOs have emerged as the predominant paradigm in the field of real-time object detection owing to their effective balance between computational cost and detection performance. Researchers have explored the architectural designs, optimization objectives, data augmentation strategies, and others for YOLOs, achieving notable progress. However, the reliance on the non-maximum suppression (NMS) for post-processing hampers the end-to-end deployment of YOLOs and adversely impacts the inference latency. Besides, the design of various components in YOLOs lacks the comprehensive and thorough inspection, resulting in noticeable computational redundancy and limiting the model's capability. It renders the suboptimal efficiency, along with considerable potential for performance improvements. In this work, we aim to further advance the performance-efficiency boundary of YOLOs from both the post-processing and model architecture. To this end, we first present the consistent dual assignments for NMS-free training of YOLOs, which brings competitive performance and low inference latency simultaneously. Moreover, we introduce the holistic efficiency-accuracy driven model design strategy for YOLOs. We comprehensively optimize various components of YOLOs from both efficiency and accuracy perspectives, which greatly reduces the computational overhead and enhances the capability. The outcome of our effort is a new generation of YOLO series for real-time end-to-end object detection, dubbed YOLOv10. Extensive experiments show that YOLOv10 achieves state-of-the-art performance and efficiency across various model scales. For example, our YOLOv10-S is 1.8$\times$ faster than RT-DETR-R18 under the similar AP on COCO, meanwhile enjoying 2.8$\times$ smaller number of parameters and FLOPs. Compared with YOLOv9-C, YOLOv10-B has 46\% less latency and 25\% fewer parameters for the same performance.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 39 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Unlocking the Visual Record of Materials Science: A Large-Scale Multimodal Dataset from Scientific Literature

    cs.CV 2026-06 accept novelty 8.0

    MatMMExtract pipeline creates MatSciFig dataset of 391k annotated materials science figure panels and MaterialScope detection dataset with high accuracy.

  2. M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection

    cs.CV 2026-05 conditional novelty 8.0

    M²E-UAV is the first benchmark dataset and evaluation protocol for tiny UAV detection from a moving event camera in motion-on-motion conditions.

  3. M$^2$E-UAV: A Benchmark and Analysis for Onboard Motion-on-Motion Event-Based Tiny UAV Detection

    cs.CV 2026-05 unverdicted novelty 7.0

    M²E-UAV provides a new benchmark and point-based baselines for event-camera tiny-UAV detection under motion-on-motion conditions, achieving 0.55 mAP50-95.

  4. Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series

    cs.CV 2026-04 unverdicted novelty 7.0

    A new global corpus of dense Sentinel-1 SAR time series for 15,606 offshore wind infrastructure locations is released with baseline semantic labels and an expert benchmark, enabling analyses of deployment dynamics.

  5. Dual-Correlation Hypergraph Network for Unaligned RGBT Video Object Detection and A Large-scale Benchmark

    cs.CV 2026-07 conditional novelty 6.0

    DHNet with patch alignment and dual hypergraph fusion reaches SOTA RGBT video object detection on VT-VOD50 and the new large-scale DVT-VOD1000 benchmark.

  6. Zero-Shot Learning in Industrial Scenarios: New Large-Scale Benchmark, Challenges and Baseline

    cs.AI 2026-06 unverdicted novelty 6.0

    Presents MMIO benchmark and RTVP method achieving state-of-the-art 42.2% AP in zero-shot industrial defect detection.

  7. RefDiffNet: Learning to Expose Subtle PCB Defects Before Detection

    cs.CV 2026-05 unverdicted novelty 6.0

    RefDiffNet is a lightweight input enhancement block that uses reference image comparison to expose PCB defects, delivering up to 18% relative mAP50:95 gains across YOLO, RT-DETR, and Faster R-CNN detectors with 0.004-...

  8. Small Object Detection in Industrial Recycling: A New Dataset and YOLO Performance Evaluation

    cs.CV 2026-05 unverdicted novelty 6.0

    Releases a recycling-specific dataset of >10k images and evaluates YOLO variants on small dense overlapping objects with augmentation and anomaly detection.

  9. BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation

    cs.CV 2026-05 unverdicted novelty 6.0

    BabelDOC uses an intermediate representation to decouple layout from content for improved layout-preserving PDF translation.

  10. DM$^3$-Nav: Decentralized Multi-Agent Multimodal Multi-Object Semantic Navigation

    cs.MA 2026-04 unverdicted novelty 6.0

    DM³-Nav delivers decentralized multi-agent semantic navigation for multimodal open-vocabulary multi-object tasks that matches centralized baselines in simulation and succeeds in real-world robot deployments.

  11. Global Offshore Wind Infrastructure: Deployment and Operational Dynamics from Dense Sentinel-1 Time Series

    cs.CV 2026-04 accept novelty 6.0

    A global Sentinel-1 SAR time series dataset of 14.8M 1D backscatter profiles at 15,606 offshore wind infrastructure locations with a rule-based event classifier (macro F1=0.84) and a 553-series expert-annotated benchmark.

  12. Tracing 3D Anatomy in 2D Strokes: A Multi-Stage Projection Driven Approach to Cervical Spine Fracture Identification

    cs.CV 2026-01 conditional novelty 6.0

    Cervical spine fractures can be detected from vertebra volumes reconstructed from 2D CT projections at F1 68.15 (vertebra) and 82.26 (patient), matching a reproduced 3D winner within about 1 point.

  13. SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition

    cs.CV 2025-05 unverdicted novelty 6.0

    SoftHGNN introduces differentiable soft hyperedges via learnable prototypes and top-k sparse selection to model high-order visual interactions and improve recognition accuracy.

  14. YOLOv12: Attention-Centric Real-Time Object Detectors

    cs.CV 2025-02 unverdicted novelty 6.0

    YOLOv12 is a new attention-based real-time object detector that reports higher accuracy than YOLOv10, YOLOv11, and RT-DETR variants at comparable or better speed and efficiency.

  15. Progressive Pixel-Neighborhood Deformable Cross-Attention for Multispectral Object Detection

    cs.CV 2026-06 unverdicted novelty 5.0

    PNAFusion proposes pixel-neighborhood cross-attention and adaptive deformable alignment integrated progressively to boost efficiency and accuracy in multispectral object detection.

  16. TinyFormer: Preserving Tiny Objects in YOLO-DETR Hybrid Real-time Detectors

    cs.CV 2026-05 unverdicted novelty 5.0

    TinyFormer adds Parallel Bi-fusion Module and Spatial Semantic Adapter to a YOLO-DETR hybrid, raising small-object AP by 1.6 points to 58.5% on MS COCO while keeping real-time speed.

  17. STAR-IOD: Scale-decoupled Topology Alignment with Pseudo-label Refinement for Remote Sensing Incremental Object Detection

    cs.CV 2026-05 unverdicted novelty 5.0

    STAR-IOD applies scale-decoupled topology alignment and K-Means-based pseudo-label refinement to reduce catastrophic forgetting in remote sensing incremental object detection, reporting 1.7% and 2.1% mAP gains on new ...

  18. Deep Learning-Based Computer Vision for Beam Selection and Proactive Blockage Prediction

    eess.SP 2026-05 unverdicted novelty 5.0

    Vision-aided deep learning delivers 98.96% beam prediction accuracy and over 98% proactive blockage prediction for mm-wave links, including the first treatment of simultaneous non-uniform mobility.

  19. A Real-time Scale-robust Network for Glottis Segmentation in Nasal Transnasal Intubation

    eess.IV 2026-04 unverdicted novelty 5.0

    A scale-robust lightweight CNN for glottis segmentation achieves 92.9% mDice at over 170 FPS with a 19 MB model size on three datasets.

  20. DocRevive: A Unified Pipeline for Document Text Restoration

    cs.CV 2026-04 unverdicted novelty 5.0

    A unified pipeline using OCR, inpainting, and diffusion models restores text in degraded documents on a new synthetic benchmark dataset, evaluated with the proposed UCSM metric.

  21. DocRevive: A Unified Pipeline for Document Text Restoration

    cs.CV 2026-04 unverdicted novelty 5.0

    DocRevive builds a unified pipeline using OCR, image analysis, language models, and diffusion to reconstruct degraded document text, backed by a 30k-image synthetic dataset and the UCSM metric.

  22. UAVDB: Point-Guided Masks for UAV Detection and Segmentation

    cs.CV 2024-09 unverdicted novelty 5.0

    Introduces UAVDB dataset for UAV detection/segmentation via PIC point-to-box conversion and SAM2 masks, with YOLO baselines showing PIC+SAM2 outperforms prior annotation methods on IoU.

  23. An Intelligent-Cloud Edge Multimodal Interaction System for Robots

    cs.RO 2026-07 conditional novelty 4.0

    A cloud-edge robot system combined a CBAM/DIoU-enhanced YOLO11n gesture detector with LLM/VLM agents, reporting 95–98.9% precision and 82–95% task success on small, validation-based evaluations.

  24. Thresholded Cross-Attention for Reliable Intensity-Chromaticity Fusion in Low-Light Image Enhancement

    cs.CV 2026-07 conditional novelty 4.0

    TCA-Net improves low-light image enhancement by replacing fixed-quota Top-K attention with an adaptive confidence threshold for intensity-chromaticity fusion in the HVI color space.

  25. A Multi-Task Deep Learning Framework for Real-Time Intelligent Video Surveillance with Temporal Event Validation

    cs.CV 2026-07 conditional novelty 4.0

    Temporal multi-frame validation around concurrent CV detectors cuts fire false alarms from 52% to 4% and lifts video plate exact-match from 66.7% to 81.8% at real-time latency on one commodity GPU.

  26. Structure-Guided Mixed Masked Pretraining and Spatial Continuity Regularization for Printed Circuit Board Defect Detection

    cs.CV 2026-06 unverdicted novelty 4.0

    A new PCB defect detection method using structure-guided masked pretraining and spatial continuity regularization achieves 85.5% mAP0.5 on the DsPCBSD+ dataset.

  27. Hierarchically Decoupled Mixture-of-Experts for Robust Traffic Sign Recognition in Complex Driving Scenarios

    cs.CV 2026-06 unverdicted novelty 4.0

    A hierarchically decoupled heterogeneous MoE framework with YOLO experts and lightweight gating network reports 76.8% mAP50-95 on a composite traffic sign dataset, a 2.3% gain over baseline with 39.4% lower compute.

  28. Sustainable Intelligence for the Wild: Democratizing Ecological Monitoring via Knowledge-Adaptive Edge Expert Agents

    cs.AI 2026-05 unverdicted novelty 4.0

    Proposes a knowledge-adaptive edge expert agent architecture for sustainable biodiversity monitoring that separates visual perception from reasoning with an explicit knowledge base.

  29. CollabOD: Collaborative Multi-Backbone with Cross-scale Vision for UAV Small Object Detection

    cs.CV 2026-03 conditional novelty 4.0

    CollabOD improves UAV small-object detection via dual-path detail preservation, dense aggregation, bilateral reweighting, and a reparameterized detail-aware head, reporting 52.4 AP50 on VisDrone at 65.5 GFLOPs.

  30. YOLO-Master: MOE-Accelerated with Specialized Transformers for Enhanced Real-time Detection

    cs.CV 2025-12 conditional novelty 4.0

    YOLO-Master inserts a sparse Mixture-of-Experts block into a YOLO backbone, reporting 42.4% COCO AP at 1.62 ms, +0.8 AP and 18% faster than YOLOv13-N.

  31. PaveSync: A Unified and Comprehensive Dataset for Pavement Distress Analysis and Classification

    cs.CV 2025-12 conditional novelty 4.0

    PaveSync merges existing pavement imagery into a standardized 52,747-image, 13-class detection dataset and benchmarks seven object detectors on it.

  32. A Survey on the Applications of Generative Artificial Intelligence in Automated Driving Systems Test Scenario Generation Methods

    cs.SE 2025-12 reject novelty 4.0

    A literature survey of scenario-generation methods for ADS testing that adds an unvalidated AII/RAS/OCS metric suite and ODD-difficulty schema, undermined by inconsistent calculations in the worked examples.

  33. DFIR-DETR: Frequency-Domain Iterative Refinement and Dynamic Feature Aggregation for Small Object Detection

    cs.CV 2025-12 unverdicted novelty 4.0

    DFIR-DETR augments RT-DETR with frequency-domain iterative refinement and dynamic feature aggregation, reporting 92.9% mAP50 on NEU-DET and 51.6% on VisDrone at 11.7M parameters and 47.2 GFLOPs.

  34. MinerU: An Open-Source Solution for Precise Document Content Extraction

    cs.CV 2024-09 conditional novelty 4.0

    MinerU delivers an open-source pipeline for high-precision document content extraction by integrating specialized models with tuned preprocessing and postprocessing rules.

  35. A Goal-Oriented Networking Approach for Intelligent IoT Service Deployment

    cs.NI 2026-05 unverdicted novelty 3.0

    A multi-objective optimization framework is proposed to assess KPIs in goal-oriented IoT service deployment, with simulation results indicating network efficiency benefits.

  36. A Comparative Study of Modern Object Detectors for Robust Apple Detection in Orchard Imagery

    cs.CV 2026-04 unverdicted novelty 3.0

    YOLO11n achieves the highest mAP@0.5:0.95 of 0.6065 for apple localization, with other detectors showing trade-offs in recall and precision at low confidence thresholds.

  37. Underwater Waste Detection Using Deep Learning A Performance Comparison of YOLOv7 to 10 and Faster RCNN

    cs.CV 2025-07 unverdicted novelty 3.0

    YOLOv8 achieves the highest mAP of 80.9% for detecting 15 classes of underwater waste among the tested models.

  38. YOLOv8 to YOLO11: A Comprehensive Architecture In-depth Comparative Review

    cs.CV 2025-01 unverdicted novelty 2.0

    Comparative review of YOLOv8 to YOLO11 architectures based on papers, docs, and code inspection, noting incremental improvements and some unchanged blocks.

  39. YOLOv11: An Overview of the Key Architectural Enhancements

    cs.CV 2024-10 unverdicted novelty 1.0

    YOLOv11 adds blocks such as C3k2, SPPF, and C2PSA to improve feature extraction, mAP, and efficiency while supporting detection, segmentation, pose, and oriented detection across model sizes.