# Detection and dense prediction distillation

Area: [Knowledge distillation](https://mlsanity.com/distill/index.md). HTML: https://mlsanity.com/distill/detection-and-dense-prediction-distillation/

## Key facts

- Detection and dense prediction distillation: 451 papers on arXiv since 2021 (data through 14 Oct 2026).
- 54 of its 451 mapped papers (12%) cite “General Instance Distillation for Object Detection” (2021, arXiv 2103.02340).
- 54 of its 451 mapped papers (12%) cite “Focal and Global Knowledge Distillation for Detectors” (2021, arXiv 2111.11837).
- 6 new papers 25 Sep–14 Oct.

## Most cited here

- [General Instance Distillation for Object Detection](https://mlsanity.com/paper/2103.02340/) (2021), cited by 54 papers here
- [Focal and Global Knowledge Distillation for Detectors](https://mlsanity.com/paper/2111.11837/) (2021), cited by 54 papers here
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021), cited by 52 papers here
- [Localization Distillation for Dense Object Detection](https://mlsanity.com/paper/2102.12252/) (2021), cited by 28 papers here
- [Instance-Conditional Knowledge Distillation for Object Detection](https://mlsanity.com/paper/2110.12724/) (2021), cited by 24 papers here
- [Cross-Image Relational Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2204.06986/) (2022), cited by 24 papers here
- [BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection](https://mlsanity.com/paper/2211.09386/) (2022), cited by 21 papers here
- [Anomaly Detection via Reverse Distillation from One-Class Embedding](https://mlsanity.com/paper/2201.10703/) (2022), cited by 18 papers here
- [Towards Efficient 3D Object Detection with Knowledge Distillation](https://mlsanity.com/paper/2205.15156/) (2022), cited by 18 papers here
- [PKD: General Distillation Framework for Object Detectors via Pearson Correlation Coefficient](https://mlsanity.com/paper/2207.02039/) (2022), cited by 18 papers here

## New (25 Sep–14 Oct)

- [One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts](https://mlsanity.com/paper/2610.12448/) (2026-10-08)
- [Difference Feature Map Distillation: Transferring Inter-Sample Relational Knowledge Towards Efficient Transformer-Based Tracking](https://mlsanity.com/paper/2610.05707/) (2026-10-05)
- [Shadow Feature Refinement Network: Progressive Feature Refinement based on Knowledge Distillation for Effective Shadow Removal](https://mlsanity.com/paper/2610.05325/) (2026-10-04)
- [WinoTS: Wavelet-based Self-Distillation for Time Series Models](https://mlsanity.com/paper/2609.39337/) (2026-09-30)
- [Emergent Multi-View Geometry Through Self-Distillation](https://mlsanity.com/paper/2609.39227/) (2026-09-30)
- [SFE-VGGT: Source-Free VGGT Distillation for Event-Based Monocular Depth Estimation](https://mlsanity.com/paper/2609.36929/) (2026-09-29)