mlsanityData to 14 Oct 2026

Cascade R-CNN: Delving into High Quality Object Detection

arXiv 1712.00726 ↗First posted 3 Dec 2017cs.CVcited by 1,276

Not on the map. Why?

Cited by 31 in Knowledge distillation, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, detection performance tends to degrade with increasing the IoU thresholds. Two main factors are responsible for this: 1) overfitting during training, due to exponentially vanishing positive samples, and 2) inference-time mismatch between the IoUs for which the detector is optimal and those of the input hypotheses. A multi-stage object detection architecture, the Cascade R-CNN, is proposed to address these problems. It consists of a sequence of detectors trained with increasing IoU thresholds, to be sequentially more selective against close false positives. The detectors are trained stage by stage, leveraging the observation that the output of a detector is a good distribution for training the next higher quality detector. The resampling of progressively improved hypotheses guarantees that all detectors have a positive set of examples of equivalent size, reducing the overfitting problem. The same cascade procedure is applied at inference, enabling a closer match between the hypotheses and the detector quality of each stage. A simple implementation of the Cascade R-CNN is shown to surpass all single-model object detectors on the challenging COCO dataset. Experiments also show that the Cascade R-CNN is widely applicable across detector architectures, achieving consistent gains independently of the baseline detector strength. The code will be made available at https://github.com/zhaoweicai/cascade-rcnn.

Key facts. Cited by 1,276 papers in the map (data through 14 Oct 2026). First posted on arXiv 3 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 303; 2022: 246; 2023: 272; 2024: 222; 2025: 145; 2026: 88.

1,276 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2023Segment Anythingcited by 8,234
  3. 2022A ConvNet for the 2020scited by 3,579
  4. 2021Masked-attention Mask Transformer for Universal Image Segmentationcited by 2,351
  5. 2021Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutionscited by 1,962
  6. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,228
  7. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  8. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 823
  9. 2021PVT v2: Improved Baselines with Pyramid Vision Transformercited by 751
  10. 2022Detecting Twenty-thousand Classes using Image-level Supervisioncited by 614
  11. 2023DETRs Beat YOLOs on Real-time Object Detectioncited by 533
  12. 2021CSWin Transformer: A General Vision Transformer Backbone with Cross-Shaped Windowscited by 527
38 more
  1. 2021MViTv2: Improved Multiscale Vision Transformers for Classification and Detectioncited by 519
  2. 2022LayoutLMv3: Pre-training for Document AI with Unified Text and Image Maskingcited by 485
  3. 2022InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutionscited by 482
  4. 2021Conditional DETR for Fast Training Convergencecited by 424
  5. 2021Bottleneck Transformers for Visual Recognitioncited by 364
  6. 2021Pix2seq: A Language Modeling Framework for Object Detectioncited by 349
  7. 2022OneFormer: One Transformer to Rule Universal Image Segmentationcited by 328
  8. 2025Perception Encoder: The best visual embeddings are not at the output of the networkcited by 326
  9. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 306
  10. 2022Vision Transformer with Deformable Attentioncited by 295
  11. 2021Focal Self-attention for Local-Global Interactions in Vision Transformerscited by 288
  12. 2022Neighborhood Attention Transformercited by 239
  13. 2022TinyViT: Fast Pretraining Distillation for Small Vision Transformerscited by 234
  14. 2021PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detectioncited by 232
  15. 2021Oriented R-CNN for Object Detectioncited by 231
  16. 2021ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Biascited by 216
  17. 2021K-Net: Towards Unified Image Segmentationcited by 212
  18. 2023Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIPcited by 201
  19. 2022RTMDet: An Empirical Study of Designing Real-Time Object Detectorscited by 195
  20. 2021Boundary IoU: Improving Object-Centric Image Segmentation Evaluationcited by 188
  21. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 187
  22. 2023Cut and Learn for Unsupervised Object Detection and Instance Segmentationcited by 187
  23. 2022Focal Modulation Networkscited by 186
  24. 2021OTA: Optimal Transport Assignment for Object Detectioncited by 178
  25. 2023FLatten Transformer: Vision Transformer using Focused Linear Attentioncited by 171
  26. 2021FSCE: Few-Shot Object Detection via Contrastive Proposal Encodingcited by 168
  27. 2021Multimodal Virtual Point 3D Detectioncited by 166
  28. 2021Instances as Queriescited by 158
  29. 2021Rethinking Counting and Localization in Crowds:A Purely Point-Based Frameworkcited by 152
  30. 2022DiT: Self-supervised Pre-training for Document Image Transformercited by 152
  31. 2023PolyFormer: Referring Image Segmentation as Sequential Polygon Generationcited by 148
  32. 2022SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptationcited by 146
  33. 2023PACO: Parts and Attributes of Common Objectscited by 146
  34. 2021Offboard 3D Object Detection from Point Cloud Sequencescited by 145
  35. 2021FAIR1M: A Benchmark Dataset for Fine-grained Object Recognition in High-Resolution Remote Sensing Imagerycited by 143
  36. 2021Focal and Global Knowledge Distillation for Detectorscited by 142
  37. 2022Focal Sparse Convolutional Networks for 3D Object Detectioncited by 142
  38. 2022More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsitycited by 142

50 most cited of 1,276 All 1,276 (JSON)