# D3ETR: Decoder Distillation for Detection Transformer

arXiv: https://arxiv.org/abs/2211.09768 · HTML: https://mlsanity.com/paper/2211.09768/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Detection and dense prediction distillation, one of 12 directions in Knowledge distillation.
- Builds on 37 of its 46 references that are in the map.
- First posted on arXiv 17 Nov 2022.

## Placed in

- Knowledge distillation / [Detection and dense prediction distillation](https://mlsanity.com/distill/detection-and-dense-prediction-distillation/)

## Builds on (most cited first, 30 of 37)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [FitNets: Hints for Thin Deep Nets](https://mlsanity.com/paper/1412.6550/) (2014)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer](https://mlsanity.com/paper/1612.03928/) (2016)
- [Relational Knowledge Distillation](https://mlsanity.com/paper/1904.05068/) (2019)
- [Contrastive Representation Distillation](https://mlsanity.com/paper/1910.10699/) (2019)
- [Deep Mutual Learning](https://mlsanity.com/paper/1706.00384/) (2017)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Similarity-Preserving Knowledge Distillation](https://mlsanity.com/paper/1907.09682/) (2019)
- [DN-DETR: Accelerate DETR Training by Introducing Query DeNoising](https://mlsanity.com/paper/2203.01305/) (2022)
- [Conditional DETR for Fast Training Convergence](https://mlsanity.com/paper/2108.06152/) (2021)
- [Decoupled Knowledge Distillation](https://mlsanity.com/paper/2203.08679/) (2022)
- [On the Efficacy of Knowledge Distillation](https://mlsanity.com/paper/1910.01348/) (2019)
- [Distilling Knowledge via Knowledge Review](https://mlsanity.com/paper/2104.09044/) (2021)
- [DETRs with Hybrid Matching](https://mlsanity.com/paper/2207.13080/) (2022)
- [Focal and Global Knowledge Distillation for Detectors](https://mlsanity.com/paper/2111.11837/) (2021)
- [Rethinking Soft Labels for Knowledge Distillation: A Bias-Variance Tradeoff Perspective](https://mlsanity.com/paper/2102.00650/) (2021)
- [General Instance Distillation for Object Detection](https://mlsanity.com/paper/2103.02340/) (2021)
- [Masked Generative Distillation](https://mlsanity.com/paper/2205.01529/) (2022)
- [Distilling Object Detectors via Decoupled Features](https://mlsanity.com/paper/2103.14475/) (2021)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)

## Built on by (most cited first, 17 of 17)

- [EdgeSAM: Prompt-In-the-Loop Distillation for SAM](https://mlsanity.com/paper/2312.06660/) (2023)
- [LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection](https://mlsanity.com/paper/2406.03459/) (2024)
- [SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion](https://mlsanity.com/paper/2409.17531/) (2024)
- [Uncovering and Quantifying Social Biases in Code Generation](https://mlsanity.com/paper/2305.15377/) (2023)
- [Interactive Segment Anything NeRF with Feature Imitation](https://mlsanity.com/paper/2305.16233/) (2023)
- [3DPPE: 3D Point Positional Encoding for Multi-Camera 3D Object Detection Transformers](https://mlsanity.com/paper/2211.14710/) (2022)
- [Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models](https://mlsanity.com/paper/2410.19635/) (2024)
- [Teach-DETR: Better Training DETR with Teachers](https://mlsanity.com/paper/2211.11953/) (2022)
- [ASAG: Building Strong One-Decoder-Layer Sparse Detectors via Adaptive Sparse Anchor Generation](https://mlsanity.com/paper/2308.09242/) (2023)
- [CLoCKDistill: Consistent Location-and-Context-aware Knowledge Distillation for DETRs](https://mlsanity.com/paper/2502.10683/) (2025)
- [Uncovering and Categorizing Social Biases in Text-to-SQL](https://mlsanity.com/paper/2305.16253/) (2023)
- [OD-DETR: Online Distillation for Stabilizing Training of Detection Transformer](https://mlsanity.com/paper/2406.05791/) (2024)
- [Parallel Sentence-Level Explanation Generation for Real-World Low-Resource Scenarios](https://mlsanity.com/paper/2302.10707/) (2023)
- [Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction](https://mlsanity.com/paper/2303.10967/) (2023)
- [Improving Long Text Understanding with Knowledge Distilled from Summarization Model](https://mlsanity.com/paper/2405.04955/) (2024)
- [M^2C-EvDet: Multi-Domain Multi-Order Cross-Modal Knowledge Distillation for Event-based Object Detection](https://mlsanity.com/paper/2606.24248/) (2026)
- [Enhanced Knowledge Distillation for Detection Transformer via Teacher Prediction Refinement](https://mlsanity.com/paper/2609.19964/) (2026)

## Abstract (arXiv)

While various knowledge distillation (KD) methods in CNN-based detectors show their effectiveness in improving small students, the baselines and recipes for DETR-based detectors are yet to be built. In this paper, we focus on the transformer decoder of DETR-based detectors and explore KD methods for them. The outputs of the transformer decoder lie in random order, which gives no direct correspondence between the predictions of the teacher and the student, thus posing a challenge for knowledge distillation. To this end, we propose MixMatcher to align the decoder outputs of DETR-based teachers and students, which mixes two teacher-student matching strategies, i.e., Adaptive Matching and Fixed Matching. Specifically, Adaptive Matching applies bipartite matching to adaptively match the outputs of the teacher and the student in each decoder layer, while Fixed Matching fixes the correspondence between the outputs of the teacher and the student with the same object queries, with the teacher's fixed object queries fed to the decoder of the student as an auxiliary group. Based on MixMatcher, we build Decoder Distillation for DEtection TRansformer (D3ETR), which distills knowledge in decoder predictions and attention maps from the teachers to students. D3ETR shows superior performance on various DETR-based detectors with different backbones. For example, D3ETR improves Conditional DETR-R50-C5 by 7.8/2.4 mAP under 12/50 epochs training settings with Conditional DETR-R101-C5 as the teacher.