mlsanityData to 7 Oct 2026

S4OD: Semi-Supervised learning for Single-Stage Object Detection

arXiv 2204.04492 ↗First posted 9 Apr 2022cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Single-stage detectors suffer from extreme foreground-background class imbalance, while two-stage detectors do not. Therefore, in semi-supervised object detection, two-stage detectors can deliver remarkable performance by only selecting high-quality pseudo labels based on classification scores. However, directly applying this strategy to single-stage detectors would aggravate the class imbalance with fewer positive samples. Thus, single-stage detectors have to consider both quality and quantity of pseudo labels simultaneously. In this paper, we design a dynamic self-adaptive threshold (DSAT) strategy in classification branch, which can automatically select pseudo labels to achieve an optimal trade-off between quality and quantity. Besides, to assess the regression quality of pseudo labels in single-stage detectors, we propose a module to compute the regression uncertainty of boxes based on Non-Maximum Suppression. By leveraging only 10% labeled data from COCO, our method achieves 35.0% AP on anchor-free detector (FCOS) and 32.9% on anchor-based detector (RetinaNet).

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 36 of its 40 references that are in the map. First posted on arXiv 9 Apr 2022.

Builds on

36 of 40 references.

References · 36

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  4. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  5. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  6. 2017Mask R-CNNcited by 7,259
  7. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,410
  9. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  10. 2018YOLOv3: An Incremental Improvementcited by 2,652
  11. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  12. 2019FCOS: Fully Convolutional One-Stage Object Detectioncited by 1,573
24 more
  1. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  2. 2019MMDetection: Open MMLab Detection Toolbox and Benchmarkcited by 1,379
  3. 2017Cascade R-CNN: Delving into High Quality Object Detectioncited by 1,275
  4. 2021Swin Transformer V2: Scaling Up Capacity and Resolutioncited by 1,215
  5. 2021YOLOX: Exceeding YOLO Series in 2021cited by 1,064
  6. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  7. 2019Hybrid Task Cascade for Instance Segmentationcited by 479
  8. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  9. 2021Semi-Supervised Semantic Segmentation with Cross Pseudo Supervisioncited by 462
  10. 2020Generalized Focal Loss: Learning Qualified and Distributed Bounding Boxes for Dense Object Detectioncited by 408
  11. 2020Meta Pseudo Labelscited by 372
  12. 2019S4L: Self-Supervised Semi-Supervised Learningcited by 335
  13. 2021End-to-End Semi-Supervised Object Detection with Soft Teachercited by 315
  14. 2021Unbiased Teacher for Semi-Supervised Object Detectioncited by 305
  15. 2020A Simple Semi-Supervised Learning Framework for Object Detectioncited by 282
  16. 2021CReST: A Class-Rebalancing Self-Training Framework for Imbalanced Semi-Supervised Learningcited by 174
  17. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  18. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  19. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  20. 2021You Only Learn One Representation: Unified Network for Multiple Taskscited by 86
  21. 2021Localization Distillation for Dense Object Detectioncited by 55
  22. 2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 48
  23. 2020Interpolation-based semi-supervised learning for object detectioncited by 40
  24. 2021Combating Noise: Semi-supervised Learning by Region Uncertainty Quantificationcited by 18

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 2; 2024: 2.

6 papers.

  1. 2022Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detectioncited by 43
  2. 2023Efficient Teacher: Semi-Supervised Object Detection for YOLOv5cited by 17
  3. 2024Semi-Supervised Object Detection: A Survey on Progress from CNN to Transformercited by 4
  4. 2022Semi-supervised object detection based on single-stage detector for thighbone fracture localizationcited by 0
  5. 2023Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Imagescited by 0
  6. 2024Co-Learning: Towards Semi-Supervised Object Detection with Road-side Camerascited by 0