# Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining

arXiv: https://arxiv.org/abs/2211.03594 · HTML: https://mlsanity.com/paper/2211.03594/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 31 references that are in the map.
- First posted on arXiv 7 Nov 2022.

## Builds on (most cited first, 26 of 26)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Masked Autoencoders Are Scalable Vision Learners](https://mlsanity.com/paper/2111.06377/) (2021)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [BEiT: BERT Pre-Training of Image Transformers](https://mlsanity.com/paper/2106.08254/) (2021)
- [DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection](https://mlsanity.com/paper/2203.03605/) (2022)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [Grounded Language-Image Pre-training](https://mlsanity.com/paper/2112.03857/) (2021)
- [SimMIM: A Simple Framework for Masked Image Modeling](https://mlsanity.com/paper/2111.09886/) (2021)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [Exploring Plain Vision Transformer Backbones for Object Detection](https://mlsanity.com/paper/2203.16527/) (2022)
- [ImageNet-21K Pretraining for the Masses](https://mlsanity.com/paper/2104.10972/) (2021)
- [DAB-DETR: Dynamic Anchor Boxes are Better Queries for DETR](https://mlsanity.com/paper/2201.12329/) (2022)
- [Image as a Foreign Language: BEiT Pretraining for All Vision and Vision-Language Tasks](https://mlsanity.com/paper/2208.10442/) (2022)
- [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)
- [End-to-End Semi-Supervised Object Detection with Soft Teacher](https://mlsanity.com/paper/2106.09018/) (2021)
- [BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers](https://mlsanity.com/paper/2208.06366/) (2022)
- [Context Autoencoder for Self-Supervised Representation Learning](https://mlsanity.com/paper/2202.03026/) (2022)
- [GLIPv2: Unifying Localization and Vision-Language Understanding](https://mlsanity.com/paper/2206.05836/) (2022)
- [Dynamic Head: Unifying Object Detection Heads with Attentions](https://mlsanity.com/paper/2106.08322/) (2021)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment](https://mlsanity.com/paper/2207.13085/) (2022)
- [Contrastive Learning Rivals Masked Image Modeling in Fine-tuning via Feature Distillation](https://mlsanity.com/paper/2205.14141/) (2022)

## Built on by (most cited first, 25 of 25)

- [EVA: Exploring the Limits of Masked Visual Representation Learning at Scale](https://mlsanity.com/paper/2211.07636/) (2022)
- [DETRs Beat YOLOs on Real-time Object Detection](https://mlsanity.com/paper/2304.08069/) (2023)
- [EVA-02: A Visual Representation for Neon Genesis](https://mlsanity.com/paper/2303.11331/) (2023)
- [DETRs with Collaborative Hybrid Assignments Training](https://mlsanity.com/paper/2211.12860/) (2022)
- [D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement](https://mlsanity.com/paper/2410.13842/) (2024)
- [Cross Modal Transformer: Towards Fast and Robust 3D Object Detection](https://mlsanity.com/paper/2301.01283/) (2023)
- [LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection](https://mlsanity.com/paper/2406.03459/) (2024)
- [MS-DETR: Efficient DETR Training with Mixed Supervision](https://mlsanity.com/paper/2401.03989/) (2024)
- [Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information](https://mlsanity.com/paper/2211.09807/) (2022)
- [Uni3DETR: Unified 3D Detection Transformer](https://mlsanity.com/paper/2310.05699/) (2023)
- [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)
- [D3ETR: Decoder Distillation for Detection Transformer](https://mlsanity.com/paper/2211.09768/) (2022)
- [Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art](https://mlsanity.com/paper/2309.04902/) (2023)
- [S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations](https://mlsanity.com/paper/2306.17602/) (2023)
- [A Strong and Reproducible Object Detector with Only Public Datasets](https://mlsanity.com/paper/2304.13027/) (2023)
- [detrex: Benchmarking Detection Transformers](https://mlsanity.com/paper/2306.07265/) (2023)
- [Language-aware Multiple Datasets Detection Pretraining for DETRs](https://mlsanity.com/paper/2304.03580/) (2023)
- [Uncovering and Categorizing Social Biases in Text-to-SQL](https://mlsanity.com/paper/2305.16253/) (2023)
- [Revisiting DETR Pre-training for Object Detection](https://mlsanity.com/paper/2308.01300/) (2023)
- [DETR Doesn't Need Multi-Scale or Locality Design](https://mlsanity.com/paper/2308.01904/) (2023)
- [Real-time 3D Semantic Scene Completion Via Feature Aggregation and Conditioned Prediction](https://mlsanity.com/paper/2303.10967/) (2023)
- [Enhancing Your Trained DETRs with Box Refinement](https://mlsanity.com/paper/2307.11828/) (2023)
- [Don't let the information slip away](https://mlsanity.com/paper/2602.22595/) (2026)
- [PK-YOLO: Pretrained Knowledge Guided YOLO for Brain Tumor Detection in Multiplanar MRI Slices](https://mlsanity.com/paper/2410.21822/) (2024)

## Abstract (arXiv)

We present a strong object detector with encoder-decoder pretraining and finetuning. Our method, called Group DETR v2, is built upon a vision transformer encoder ViT-Huge~citedosovitskiy2020image, a DETR variant DINO~citezhang2022dino, and an efficient DETR training method Group DETR~citechen2022group. The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO. Group DETR v2 achieves 64.5 mAP on COCO test-dev, and establishes a new SoTA on the COCO leaderboard https://paperswithcode.com/sota/object-detection-on-coco