mlsanityData to 7 Oct 2026

Rich feature hierarchies for accurate object detection and semantic segmentation

arXiv 1311.2524 ↗First posted 11 Nov 2013cs.CVcited by 2,160

On the map: World models → World modeling from LiDAR generation

Abstract (arXiv)

Object detection performance, as measured on the canonical PASCAL VOC dataset, has plateaued in the last few years. The best-performing methods are complex ensemble systems that typically combine multiple low-level image features with high-level context. In this paper, we propose a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012---achieving a mAP of 53.3%. Our approach combines two key insights: (1) one can apply high-capacity convolutional neural networks (CNNs) to bottom-up region proposals in order to localize and segment objects and (2) when labeled training data is scarce, supervised pre-training for an auxiliary task, followed by domain-specific fine-tuning, yields a significant performance boost. Since we combine region proposals with CNNs, we call our method R-CNN: Regions with CNN features. We also compare R-CNN to OverFeat, a recently proposed sliding-window detector based on a similar CNN architecture. We find that R-CNN outperforms OverFeat by a large margin on the 200-class ILSVRC2013 detection dataset. Source code for the complete system is available at http://www.cs.berkeley.edu/~rbg/rcnn.

Key facts. Cited by 2,160 papers in the map (data through 7 Oct 2026). Placed in World modeling from LiDAR generation, one of 11 directions in World models. Builds on 0 of its 50 references that are in the map. First posted on arXiv 11 Nov 2013.

Builds on

0 of 50 references.

No references here yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2015: 2; 2016: 0; 2017: 0; 2018: 2; 2019: 1; 2020: 0; 2021: 595; 2022: 469; 2023: 446; 2024: 315; 2025: 229; 2026: 101.

2,160 papers.

Sort:

By area:

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2023Segment Anythingcited by 8,158
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timecited by 1,366
  5. 2022CoCa: Contrastive Captioners are Image-Text Foundation Modelscited by 1,265
  6. 2021Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gaugescited by 1,131
  7. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  8. 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
  9. 2024Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMscited by 822
  10. 2021Florence: A New Foundation Model for Computer Visioncited by 802
  11. 2021Domain Generalization: A Surveycited by 760
  12. 2022Exploring Plain Vision Transformer Backbones for Object Detectioncited by 723
38 more
  1. 2021BEVDet: High-performance Multi-camera 3D Object Detection in Bird-Eye-Viewcited by 711
  2. 2023ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoderscited by 703
  3. 2022EVA: Exploring the Limits of Masked Visual Representation Learning at Scalecited by 685
  4. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 655
  5. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  6. 2022Socratic Models: Composing Zero-Shot Multimodal Reasoning with Languagecited by 513
  7. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  8. 2022DN-DETR: Accelerate DETR Training by Introducing Query DeNoisingcited by 486
  9. 2021SLIP: Self-supervision meets Language-Image Pre-trainingcited by 434
  10. 2021Deep Long-Tailed Learning: A Surveycited by 416
  11. 2021Supervision Exists Everywhere: A Data Efficient Contrastive Language-Image Pre-training Paradigmcited by 405
  12. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  13. 2022DiffusionDet: Diffusion Model for Object Detectioncited by 354
  14. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 345
  15. 2021Multi-attentional Deepfake Detectioncited by 339
  16. 2021Deep ViT Features as Dense Visual Descriptorscited by 327
  17. 2021Towards Open World Object Detectioncited by 297
  18. 2024A Survey on Vision-Language-Action Models for Embodied AIcited by 274
  19. 2021Video Transformer Networkcited by 271
  20. 2021Training Spiking Neural Networks Using Lessons From Deep Learningcited by 251
  21. 2022Masked Visual Pre-training for Motor Controlcited by 246
  22. 2022Real-World Robot Learning with Masked Visual Pre-trainingcited by 241
  23. 2021Oriented R-CNN for Object Detectioncited by 230
  24. 2025SAM 3D: 3Dfy Anything in Imagescited by 230
  25. 2021Localizing Objects with Self-Supervised Transformers and no Labelscited by 227
  26. 2021A Simple Baseline for Open-Vocabulary Semantic Segmentation with Pre-trained Vision-language Modelcited by 223
  27. 2021TOOD: Task-aligned One-stage Object Detectioncited by 218
  28. 2021A Survey of Human-in-the-loop for Machine Learningcited by 214
  29. 2025REPA-E: Unlocking VAE for End-to-End Tuning with Latent Diffusion Transformerscited by 212
  30. 2021Trustworthy AI: From Principles to Practicescited by 206
  31. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 202
  32. 2021ReDet: A Rotation-equivariant Detector for Aerial Object Detectioncited by 202
  33. 2022Versatile Diffusion: Text, Images and Variations All in One Diffusion Modelcited by 199
  34. 2024Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapterscited by 199
  35. 2021Distribution Alignment: A Unified Framework for Long-tail Visual Recognitioncited by 198
  36. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 186
  37. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  38. 2021Localizing Visual Sounds the Hard Waycited by 169

50 most cited of 2,160 All 2,160 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Object Detection with Multimodal Large Vision-Language Models: An In-depth Review
  2. 2025Roboflow100-VL: A Multi-Domain Object Detection Benchmark for Vision-Language Models
  3. 2025Beyond CNNs: Efficient Fine-Tuning of Multi-Modal LLMs for Object Detection on Low-Data Regimes
  4. 2025Vision-Language Model for Object Detection and Segmentation: A Review and Evaluation
  5. 2024Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
  6. 2022Minkowski Tracker: A Sparse Spatio-Temporal R-CNN for Joint Object Detection and Tracking
  7. 2025Auto-Labeling Data for Object Detection
  8. 2024YOLO-RD: Introducing Relevant and Compact Explicit Knowledge to YOLO by Retriever-Dictionary