mlsanityData to 14 Oct 2026

An Analysis of Scale Invariance in Object Detection - SNIP

arXiv 1711.08189 ↗First posted 22 Nov 2017cs.CVcited by 120

Not on the map. Why?

Abstract (arXiv)

An analysis of different techniques for recognizing and detecting objects under extreme scale variation is presented. Scale specific and scale invariant design of detectors are compared by training them with different configurations of input data. By evaluating the performance of different network architectures for classifying small objects on ImageNet, we show that CNNs are not robust to changes in scale. Based on this analysis, we propose to train and test detectors on the same scales of an image-pyramid. Since small and large objects are difficult to recognize at smaller and larger scales respectively, we present a novel training scheme called Scale Normalization for Image Pyramids (SNIP) which selectively back-propagates the gradients of object instances of different sizes as a function of the image scale. On the COCO dataset, our single model performance is 45.7% and an ensemble of 3 networks obtains an mAP of 48.3%. We use off-the-shelf ImageNet-1000 pre-trained models and only train with bounding box supervision. Our submission won the Best Student Entry in the COCO 2017 challenge. Code will be made available at urlhttp://bit.ly/2yXVg4c.

Key facts. Cited by 120 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 39; 2022: 22; 2023: 22; 2024: 16; 2025: 12; 2026: 9.

120 papers.

Sort:

By area:

  1. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,139
  2. 2021Object Detection in Aerial Images: A Large-Scale Benchmark and Challengescited by 204
  3. 2021Embracing Single Stride 3D Object Detector with Sparse Transformercited by 193
  4. 2021Dynamic Head: Unifying Object Detection Heads with Attentionscited by 187
  5. 2021RangeDet:In Defense of Range View for LiDAR-based 3D Object Detectioncited by 140
  6. 2022UIU-Net: U-Net in U-Net for Infrared Small Object Detectioncited by 127
  7. 2022Towards Large-Scale Small Object Detection: Survey and Benchmarkscited by 122
  8. 2021You Only Look One-level Featurecited by 116
  9. 2021Aligning Pretraining for Detection via Object-Level Contrastive Learningcited by 110
  10. 2021QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detectioncited by 70
  11. 2021Spatially Consistent Representation Learningcited by 64
  12. 2021Lite Vision Transformer with Enhanced Self-Attentioncited by 64
38 more
  1. 2022Detecting tiny objects in aerial images: A normalized Wasserstein distance and a new benchmarkcited by 56
  2. 2021Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detectioncited by 53
  3. 2021A Normalized Gaussian Wasserstein Distance for Tiny Object Detectioncited by 53
  4. 2022RFLA: Gaussian Receptive Field based Label Assignment for Tiny Object Detectioncited by 51
  5. 2024Cross-Scale MAE: A Tale of Multi-Scale Exploitation in Remote Sensingcited by 47
  6. 2023Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detectioncited by 43
  7. 2021Tracking Pedestrian Heads in Dense Crowdcited by 42
  8. 2022ResFormer: Scaling ViTs with Multi-Resolution Trainingcited by 34
  9. 2022No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objectscited by 27
  10. 2021Multi-Scale Aligned Distillation for Low-Resolution Detectioncited by 24
  11. 2021Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detectioncited by 24
  12. 2021Scale-aware Automatic Augmentation for Object Detectioncited by 23
  13. 2023Image Data Augmentation Approaches: A Comprehensive Survey and Future directionscited by 23
  14. 2023End-to-End Spatio-Temporal Action Localisation with Video Transformerscited by 20
  15. 2021Dead Pixel Test Using Effective Receptive Fieldcited by 18
  16. 2021Scale-invariant scale-channel networks: Deep networks that generalise to previously unseen scalescited by 17
  17. 2022GiraffeDet: A Heavy-Neck Paradigm for Object Detectioncited by 17
  18. 2023Cascaded Zoom-in Detector for High Resolution Aerial Imagescited by 17
  19. 2021Circle Representation for Medical Object Detectioncited by 15
  20. 2022Scale-Equivalent Distillation for Semi-Supervised Object Detectioncited by 15
  21. 2022Active Pointly-Supervised Instance Segmentationcited by 15
  22. 2022YOLO-FaceV2: A Scale and Occlusion Aware Face Detectorcited by 15
  23. 2024ESOD: Efficient Small Object Detection on High-Resolution Imagescited by 15
  24. 2022SparseDet: Improving Sparsely Annotated Object Detection with Pseudo-positive Miningcited by 14
  25. 2023MixTeacher: Mining Promising Labels with Mixed Scale Teacher for Semi-Supervised Object Detectioncited by 13
  26. 2021Infrared Small-Dim Target Detection with Transformer under Complex Backgroundscited by 12
  27. 2021YOLO-Z: Improving small object detection in YOLOv5 for autonomous vehiclescited by 12
  28. 2022You Should Look at All Objectscited by 12
  29. 2021AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenescited by 11
  30. 2021Improved YOLOv5 network for real-time multi-scale traffic sign detectioncited by 11
  31. 2024YOLC: You Only Look Clusters for Tiny Object Detection in Aerial Imagescited by 11
  32. 2021MogFace: Towards a Deeper Appreciation on Face Detectioncited by 10
  33. 2021USB: Universal-Scale Object Detection Benchmarkcited by 10
  34. 2021Towards Balanced Learning for Instance Recognitioncited by 9
  35. 2021Tiny Obstacle Discovery by Occlusion-Aware Multilayer Regressioncited by 9
  36. 2023Is Underwater Image Enhancement All Object Detectors Need?cited by 9
  37. 2024Visible and Clear: Finding Tiny Objects in Difference Mapcited by 9
  38. 2021Gaining Scale Invariance in UAV Bird's Eye View Object Detection by Adaptive Resizingcited by 8

50 most cited of 120 All 120 (JSON)