# DETReg: Unsupervised Pretraining with Region Priors for Object Detection

arXiv: https://arxiv.org/abs/2106.04550 · HTML: https://mlsanity.com/paper/2106.04550/

## Key facts

- Cited by 76 papers in the map (data through 14 Oct 2026).
- Builds on 54 of its 82 references that are in the map.
- First posted on arXiv 8 Jun 2021.

## Builds on (most cited first, 30 of 54)

- [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)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [End-to-End Object Detection with Transformers](https://mlsanity.com/paper/2005.12872/) (2020)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Deformable DETR: Deformable Transformers for End-to-End Object Detection](https://mlsanity.com/paper/2010.04159/) (2020)
- [Fast R-CNN](https://mlsanity.com/paper/1504.08083/) (2015)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Rich feature hierarchies for accurate object detection and semantic segmentation](https://mlsanity.com/paper/1311.2524/) (2013)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Unsupervised Representation Learning by Predicting Image Rotations](https://mlsanity.com/paper/1803.07728/) (2018)
- [ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness](https://mlsanity.com/paper/1811.12231/) (2018)
- [YOLO9000: Better, Faster, Stronger](https://mlsanity.com/paper/1612.08242/) (2016)
- [Context Encoders: Feature Learning by Inpainting](https://mlsanity.com/paper/1604.07379/) (2016)
- [Big Self-Supervised Models are Strong Semi-Supervised Learners](https://mlsanity.com/paper/2006.10029/) (2020)
- [Generalized Intersection over Union: A Metric and A Loss for Bounding Box Regression](https://mlsanity.com/paper/1902.09630/) (2019)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [Colorful Image Colorization](https://mlsanity.com/paper/1603.08511/) (2016)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [Deep Clustering for Unsupervised Learning of Visual Features](https://mlsanity.com/paper/1807.05520/) (2018)
- [Self-Supervised Learning of Pretext-Invariant Representations](https://mlsanity.com/paper/1912.01991/) (2019)
- [Focal Loss for Dense Object Detection](https://mlsanity.com/paper/1708.02002/) (2017)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [Rethinking ImageNet Pre-training](https://mlsanity.com/paper/1811.08883/) (2018)
- [Unbiased Teacher for Semi-Supervised Object Detection](https://mlsanity.com/paper/2102.09480/) (2021)

## Built on by (most cited first, 30 of 76)

- [Visual Prompting via Image Inpainting](https://mlsanity.com/paper/2209.00647/) (2022)
- [A Cookbook of Self-Supervised Learning](https://mlsanity.com/paper/2304.12210/) (2023)
- [Cut and Learn for Unsupervised Object Detection and Instance Segmentation](https://mlsanity.com/paper/2301.11320/) (2023)
- [FreeSOLO: Learning to Segment Objects without Annotations](https://mlsanity.com/paper/2202.12181/) (2022)
- [Class-agnostic Object Detection with Multi-modal Transformer](https://mlsanity.com/paper/2111.11430/) (2021)
- [To Compress or Not to Compress- Self-Supervised Learning and Information Theory: A Review](https://mlsanity.com/paper/2304.09355/) (2023)
- [MobileSAMv2: Faster Segment Anything to Everything](https://mlsanity.com/paper/2312.09579/) (2023)
- [A Survey of Self-Supervised and Few-Shot Object Detection](https://mlsanity.com/paper/2110.14711/) (2021)
- [Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection](https://mlsanity.com/paper/2204.02964/) (2022)
- [Continual Object Detection: A review of definitions, strategies, and challenges](https://mlsanity.com/paper/2205.15445/) (2022)
- [Object Detection with Transformers: A Review](https://mlsanity.com/paper/2306.04670/) (2023)
- [Proper Reuse of Image Classification Features Improves Object Detection](https://mlsanity.com/paper/2204.00484/) (2022)
- [FS-DETR: Few-Shot DEtection TRansformer with prompting and without re-training](https://mlsanity.com/paper/2210.04845/) (2022)
- [MOVE: Unsupervised Movable Object Segmentation and Detection](https://mlsanity.com/paper/2210.07920/) (2022)
- [MOST: Multiple Object localization with Self-supervised Transformers for object discovery](https://mlsanity.com/paper/2304.05387/) (2023)
- [CuVLER: Enhanced Unsupervised Object Discoveries through Exhaustive Self-Supervised Transformers](https://mlsanity.com/paper/2403.07700/) (2024)
- [Object Detection in Autonomous Vehicles: Status and Open Challenges](https://mlsanity.com/paper/2201.07706/) (2022)
- [AlignDet: Aligning Pre-training and Fine-tuning in Object Detection](https://mlsanity.com/paper/2307.11077/) (2023)
- [DeNVeR: Deformable Neural Vessel Representations for Unsupervised Video Vessel Segmentation](https://mlsanity.com/paper/2406.01591/) (2024)
- [Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes](https://mlsanity.com/paper/2407.11464/) (2024)
- [Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt](https://mlsanity.com/paper/2302.01171/) (2023)
- [DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection](https://mlsanity.com/paper/2406.14924/) (2024)
- [A Comparative Review of Recent Few-Shot Object Detection Algorithms](https://mlsanity.com/paper/2111.00201/) (2021)
- [Dynamic Curriculum Learning for Great Ape Detection in the Wild](https://mlsanity.com/paper/2205.00275/) (2022)
- [Towards Efficient Use of Multi-Scale Features in Transformer-Based Object Detectors](https://mlsanity.com/paper/2208.11356/) (2022)
- [IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks](https://mlsanity.com/paper/2312.01771/) (2023)
- [Open-world Instance Segmentation: Top-down Learning with Bottom-up Supervision](https://mlsanity.com/paper/2303.05503/) (2023)
- [Siamese DETR](https://mlsanity.com/paper/2303.18144/) (2023)
- [LORE++: Logical Location Regression Network for Table Structure Recognition with Pre-training](https://mlsanity.com/paper/2401.01522/) (2024)
- [Scaling Novel Object Detection with Weakly Supervised Detection Transformers](https://mlsanity.com/paper/2207.05205/) (2022)

## Abstract (arXiv)

Recent self-supervised pretraining methods for object detection largely focus on pretraining the backbone of the object detector, neglecting key parts of detection architecture. Instead, we introduce DETReg, a new self-supervised method that pretrains the entire object detection network, including the object localization and embedding components. During pretraining, DETReg predicts object localizations to match the localizations from an unsupervised region proposal generator and simultaneously aligns the corresponding feature embeddings with embeddings from a self-supervised image encoder. We implement DETReg using the DETR family of detectors and show that it improves over competitive baselines when finetuned on COCO, PASCAL VOC, and Airbus Ship benchmarks. In low-data regimes DETReg achieves improved performance, e.g., when training with only 1% of the labels and in the few-shot learning settings.