mlsanityData to 7 Oct 2026

YOLOv9: Learning What You Want to Learn Using Programmable Gradient Information

arXiv 2402.13616 ↗First posted 21 Feb 2024cs.CVcited by 422

Not on the map. Why?

Abstract (arXiv)

Today's deep learning methods focus on how to design the most appropriate objective functions so that the prediction results of the model can be closest to the ground truth. Meanwhile, an appropriate architecture that can facilitate acquisition of enough information for prediction has to be designed. Existing methods ignore a fact that when input data undergoes layer-by-layer feature extraction and spatial transformation, large amount of information will be lost. This paper will delve into the important issues of data loss when data is transmitted through deep networks, namely information bottleneck and reversible functions. We proposed the concept of programmable gradient information (PGI) to cope with the various changes required by deep networks to achieve multiple objectives. PGI can provide complete input information for the target task to calculate objective function, so that reliable gradient information can be obtained to update network weights. In addition, a new lightweight network architecture -- Generalized Efficient Layer Aggregation Network (GELAN), based on gradient path planning is designed. GELAN's architecture confirms that PGI has gained superior results on lightweight models. We verified the proposed GELAN and PGI on MS COCO dataset based object detection. The results show that GELAN only uses conventional convolution operators to achieve better parameter utilization than the state-of-the-art methods developed based on depth-wise convolution. PGI can be used for variety of models from lightweight to large. It can be used to obtain complete information, so that train-from-scratch models can achieve better results than state-of-the-art models pre-trained using large datasets, the comparison results are shown in Figure 1. The source codes are at: https://github.com/WongKinYiu/yolov9.

Key facts. Cited by 422 papers in the map (data through 7 Oct 2026). Builds on 78 of its 80 references that are in the map. First posted on arXiv 21 Feb 2024.

Builds on

78 of 80 references.

References · 78

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2020End-to-End Object Detection with Transformerscited by 7,384
  6. 2016Densely Connected Convolutional Networkscited by 6,691
  7. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  8. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  9. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  10. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
  11. 2014Going Deeper with Convolutionscited by 4,231
  12. 2022A ConvNet for the 2020scited by 3,545
38 more
  1. 2018YOLOv3: An Incremental Improvementcited by 2,652
  2. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  3. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  4. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,960
  6. 2020YOLOv4: Optimal Speed and Accuracy of Object Detectioncited by 1,624
  7. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
  8. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  9. 2019Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regressioncited by 1,361
  10. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  11. 2021SimMIM: A Simple Framework for Masked Image Modelingcited by 1,147
  12. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  13. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  14. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  15. 2022YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectorscited by 978
  16. 2024VMamba: Visual State Space Modelcited by 955
  17. 2018Path Aggregation Network for Instance Segmentationcited by 796
  18. 2015Deep Learning and the Information Bottleneck Principlecited by 793
  19. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 749
  20. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  21. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  22. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 526
  23. 2022MaxViT: Multi-Axis Vision Transformercited by 476
  24. 2019Res2Net: A New Multi-scale Backbone Architecturecited by 468
  25. 2019Distance-IoU Loss: Faster and Better Learning for Bounding Box Regressioncited by 454
  26. 2019CSPNet: A New Backbone that can Enhance Learning Capability of CNNcited by 381
  27. 2014Deeply-Supervised Netscited by 364
  28. 2022YOLOv6: A Single-Stage Object Detection Framework for Industrial Applicationscited by 273
  29. 2022DETRs with Collaborative Hybrid Assignments Trainingcited by 273
  30. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  31. 2017The Reversible Residual Network: Backpropagation Without Storing Activationscited by 215
  32. 2020Scaled-YOLOv4: Scaling Cross Stage Partial Networkcited by 211
  33. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 192
  34. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 177
  35. 2022DaViT: Dual Attention Vision Transformerscited by 174
  36. 2020FCOS: A simple and strong anchor-free object detectorcited by 171
  37. 2019IoU Loss for 2D/3D Object Detectioncited by 128
  38. 2021Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Taskscited by 124

50 most cited of 78 All 78 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 128; 2025: 181; 2026: 113.

422 papers.

Sort:

By area:

  1. 2024YOLOv10: Real-Time End-to-End Object Detectioncited by 508
  2. 2024YOLOv11: An Overview of the Key Architectural Enhancementscited by 414
  3. 2025YOLOv12: Attention-Centric Real-Time Object Detectorscited by 300
  4. 2024RT-DETRv2: Improved Baseline with Bag-of-Freebies for Real-Time Detection Transformercited by 88
  5. 2025YOLO26: Key Architectural Enhancements and Performance Benchmarking for Real-Time Object Detectioncited by 76
  6. 2024D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinementcited by 73
  7. 2025RF-DETR: Neural Architecture Search for Real-Time Detection Transformerscited by 70
  8. 2024DEIM: DETR with Improved Matching for Fast Convergencecited by 67
  9. 2025Multi-subject Open-set Personalization in Video Generationcited by 65
  10. 2025YOLOv13: Real-Time Object Detection with Hypergraph-Enhanced Adaptive Visual Perceptioncited by 57
  11. 2024Make It Count: Text-to-Image Generation with an Accurate Number of Objectscited by 47
  12. 2026Ultralytics YOLO26: Unified Real-Time End-to-End Vision Modelscited by 47
38 more
  1. 2024DRCT: Saving Image Super-resolution away from Information Bottleneckcited by 40
  2. 2024RT-DETRv3: Real-time End-to-End Object Detection with Hierarchical Dense Positive Supervisioncited by 31
  3. 2024Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computationcited by 29
  4. 2025Real-Time Object Detection Meets DINOv3cited by 26
  5. 2024YOLO Evolution: A Comprehensive Benchmark and Architectural Review of YOLOv12, YOLO11, and Their Previous Versionscited by 18
  6. 2024Pelican: Correcting Hallucination in Vision-LLMs via Claim Decomposition and Program of Thought Verificationcited by 17
  7. 2025Ultralytics YOLO Evolution: An Overview of YOLO27, YOLO26, YOLO11, YOLOv8, and YOLOv5 Object Detectors for Computer Vision and Pattern Recognitioncited by 17
  8. 2024The 8th AI City Challengecited by 15
  9. 2025UAV-DETR: Efficient End-to-End Object Detection for Unmanned Aerial Vehicle Imagerycited by 15
  10. 2025YOLOv8 to YOLO11: A Comprehensive Architecture In-depth Comparative Reviewcited by 15
  11. 2024Pytorch-Wildlife: A Collaborative Deep Learning Framework for Conservationcited by 14
  12. 2024YOLOv1 to YOLOv10: A comprehensive review of YOLO variants and their application in the agricultural domaincited by 14
  13. 2025FBRT-YOLO: Faster and Better for Real-Time Aerial Image Detectioncited by 13
  14. 2025Tora2: Motion and Appearance Customized Diffusion Transformer for Multi-Entity Video Generationcited by 12
  15. 2025Securing the Skies: A Comprehensive Survey on Anti-UAV Methods, Benchmarking, and Future Directionscited by 11
  16. 2025Unlearning Sensitive Information in Multimodal LLMs: Benchmark and Attack-Defense Evaluationcited by 11
  17. 2026LPM 1.0: Video-based Character Performance Modelcited by 11
  18. 2024YOLOv9 for Fracture Detection in Pediatric Wrist Trauma X-ray Imagescited by 10
  19. 2024Advanced computer vision for extracting georeferenced vehicle trajectories from drone imagerycited by 10
  20. 2025SICNav-Diffusion: Safe and Interactive Crowd Navigation with Diffusion Trajectory Predictionscited by 10
  21. 20254D Gaussian Splatting SLAMcited by 10
  22. 2024Multi-Modal UAV Detection, Classification and Tracking Algorithm -- Technical Report for CVPR 2024 UG2 Challengecited by 9
  23. 2024SCSA: Exploring the Synergistic Effects Between Spatial and Channel Attentioncited by 9
  24. 2024WARM-3D: A Weakly-Supervised Sim2Real Domain Adaptation Framework for Roadside Monocular 3D Object Detectioncited by 9
  25. 2024RemDet: Rethinking Efficient Model Design for UAV Object Detectioncited by 9
  26. 2025Road Damage and Manhole Detection using Deep Learning for Smart Cities: A Polygonal Annotation Approachcited by 9
  27. 2026Articulated 3D Scene Graphs for Open-World Mobile Manipulationcited by 9
  28. 2024Prompt-Based Segmentation at Multiple Resolutions and Lighting Conditions using Segment Anything Model 2cited by 8
  29. 2024SynDroneVision: A Synthetic Dataset for Image-Based Drone Detectioncited by 8
  30. 2025M4-SAR: A Multi-Resolution, Multi-Polarization, Multi-Scene, Multi-Source Dataset and Benchmark for optical-SAR Object Detectioncited by 8
  31. 2024PolypDB: A Curated Multi-Center Dataset for Development of AI Algorithms in Colonoscopycited by 7
  32. 2024CCi-YOLOv8n: Enhanced Fire Detection with CARAFE and Context-Guided Modulescited by 7
  33. 2024FAST-Splat: Fast, Ambiguity-Free Semantics Transfer in Gaussian Splattingcited by 7
  34. 2024Comparative Analysis of YOLOv9, YOLOv10 and RT-DETR for Real-Time Weed Detectioncited by 7
  35. 2025SU-YOLO: Spiking Neural Network for Efficient Underwater Object Detectioncited by 7
  36. 2025Data Leakage in Visual Datasetscited by 7
  37. 2024EditScribe: Non-Visual Image Editing with Natural Language Verification Loopscited by 6
  38. 2024YOLOv1 to YOLOv10: The fastest and most accurate real-time object detection systemscited by 6

50 most cited of 422 All 422 (JSON)