mlsanityData to 7 Oct 2026

Interpolation-based semi-supervised learning for object detection

arXiv 2006.02158 ↗First posted 3 Jun 2020cs.CVcited by 40

Not on the map. Why?

Abstract (arXiv)

Despite the data labeling cost for the object detection tasks being substantially more than that of the classification tasks, semi-supervised learning methods for object detection have not been studied much. In this paper, we propose an Interpolation-based Semi-supervised learning method for object Detection (ISD), which considers and solves the problems caused by applying conventional Interpolation Regularization (IR) directly to object detection. We divide the output of the model into two types according to the objectness scores of both original patches that are mixed in IR. Then, we apply a separate loss suitable for each type in an unsupervised manner. The proposed losses dramatically improve the performance of semi-supervised learning as well as supervised learning. In the supervised learning setting, our method improves the baseline methods by a significant margin. In the semi-supervised learning setting, our algorithm improves the performance on a benchmark dataset (PASCAL VOC and MSCOCO) in a benchmark architecture (SSD).

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 3 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 14; 2023: 12; 2024: 3; 2025: 1; 2026: 1.

40 papers.

Sort:

  1. 2021Humble Teachers Teach Better Students for Semi-Supervised Object Detectioncited by 115
  2. 2021Instant-Teaching: An End-to-End Semi-Supervised Object Detection Frameworkcited by 112
  3. 2022Semi-Supervised and Unsupervised Deep Visual Learning: A Surveycited by 52
  4. 2021Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detectioncited by 48
  5. 2022Consistent-Teacher: Towards Reducing Inconsistent Pseudo-targets in Semi-supervised Object Detectioncited by 43
  6. 2023Active Teacher for Semi-Supervised Object Detectioncited by 43
  7. 2021Semi-Supervised Object Detection with Adaptive Class-Rebalancing Self-Trainingcited by 28
  8. 2021Not All Labels Are Equal: Rationalizing The Labeling Costs for Training Object Detectioncited by 27
  9. 2022Imposing Consistency for Optical Flow Estimationcited by 24
  10. 2022Mix-Teaching: A Simple, Unified and Effective Semi-Supervised Learning Framework for Monocular 3D Object Detectioncited by 23
  11. 2021MUM : Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detectioncited by 21
  12. 2021Combating Noise: Semi-supervised Learning by Region Uncertainty Quantificationcited by 18
28 more
  1. 2022End-to-End Semi-Supervised Learning for Video Action Detectioncited by 17
  2. 2023DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labelingcited by 14
  3. 2024OCAI: Improving Optical Flow Estimation by Occlusion and Consistency Aware Interpolationcited by 11
  4. 2022SIOD: Single Instance Annotated Per Category Per Image for Object Detectioncited by 10
  5. 2022Point-Teaching: Weakly Semi-Supervised Object Detection with Point Annotationscited by 10
  6. 2023Mixed Pseudo Labels for Semi-Supervised Object Detectioncited by 10
  7. 2021WSSOD: A New Pipeline for Weakly- and Semi-Supervised Object Detectioncited by 7
  8. 2024ACTRESS: Active Retraining for Semi-supervised Visual Groundingcited by 7
  9. 2022CrossRectify: Leveraging Disagreement for Semi-supervised Object Detectioncited by 6
  10. 2022S4OD: Semi-Supervised learning for Single-Stage Object Detectioncited by 6
  11. 2022MixupE: Understanding and Improving Mixup from Directional Derivative Perspectivecited by 6
  12. 2022Semi-Supervised Object Detection with Object-wise Contrastive Learning and Regression Uncertaintycited by 5
  13. 2023Semi-supervised Object Detection: A Survey on Recent Research and Progresscited by 5
  14. 2023Pseudo-label Correction and Learning For Semi-Supervised Object Detectioncited by 3
  15. 2023Supervision Interpolation via LossMix: Generalizing Mixup for Object Detection and Beyondcited by 3
  16. 2021Frequency Spectrum Augmentation Consistency for Domain Adaptive Object Detectioncited by 2
  17. 2022Semi-Weakly Supervised Object Detection by Sampling Pseudo Ground-Truth Boxescited by 2
  18. 2022Non-iterative optimization of pseudo-labeling thresholds for training object detection models from multiple datasetscited by 2
  19. 2023Semi-Supervised and Long-Tailed Object Detection with CascadeMatchcited by 2
  20. 2023Towards End-to-end Semi-supervised Learning for One-stage Object Detectioncited by 1
  21. 2023Pseudo-Labeling Enhanced by Privileged Information and Its Application to In Situ Sequencing Imagescited by 1
  22. 2023Refining the ONCE Benchmark with Hyperparameter Tuningcited by 1
  23. 2025Exploring Scale Shift in Crowd Localization under the Context of Domain Generalizationcited by 1
  24. 2026Performance-guided Reinforced Active Learning for Object Detectioncited by 1
  25. 2022Towards Accurate and Robust Classification in Continuously Transitioning Industrial Sprays with Mixupcited by 0
  26. 2023Aligning Data Selection with Performance: Performance-driven Reinforcement Learning for Active Learning in Object Detectioncited by 0
  27. 2023Rethinking Scale Imbalance in Semi-supervised Object Detection for Aerial Imagescited by 0
  28. 2024SemiAdv: Query-Efficient Black-Box Adversarial Attack with Unlabeled Imagescited by 0