# Point-Level Region Contrast for Object Detection Pre-Training

arXiv: https://arxiv.org/abs/2202.04639 · HTML: https://mlsanity.com/paper/2202.04639/

## Key facts

- Cited by 41 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 52 references that are in the map.
- First posted on arXiv 9 Feb 2022.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [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)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks](https://mlsanity.com/paper/1506.01497/) (2015)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Representation Learning with Contrastive Predictive Coding](https://mlsanity.com/paper/1807.03748/) (2018)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [The Cityscapes Dataset for Semantic Urban Scene Understanding](https://mlsanity.com/paper/1604.01685/) (2016)
- [SSD: Single Shot MultiBox Detector](https://mlsanity.com/paper/1512.02325/) (2015)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distances](https://mlsanity.com/paper/1306.0895/) (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)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination](https://mlsanity.com/paper/1805.01978/) (2018)
- [Contrastive Multiview Coding](https://mlsanity.com/paper/1906.05849/) (2019)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Data-Efficient Image Recognition with Contrastive Predictive Coding](https://mlsanity.com/paper/1905.09272/) (2019)
- [Simple Copy-Paste is a Strong Data Augmentation Method for Instance Segmentation](https://mlsanity.com/paper/2012.07177/) (2020)
- [Dense Contrastive Learning for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2011.09157/) (2020)
- [PointContrast: Unsupervised Pre-training for 3D Point Cloud Understanding](https://mlsanity.com/paper/2007.10985/) (2020)
- [PointRend: Image Segmentation as Rendering](https://mlsanity.com/paper/1912.08193/) (2019)
- [With a Little Help from My Friends: Nearest-Neighbor Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2104.14548/) (2021)

## Built on by (most cited first, 30 of 41)

- [Region-Aware Pretraining for Open-Vocabulary Object Detection with Vision Transformers](https://mlsanity.com/paper/2305.07011/) (2023)
- [Hyperbolic Contrastive Learning for Visual Representations beyond Objects](https://mlsanity.com/paper/2212.00653/) (2022)
- [Contrastive Mean Teacher for Domain Adaptive Object Detectors](https://mlsanity.com/paper/2305.03034/) (2023)
- [CoDet: Co-Occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection](https://mlsanity.com/paper/2310.16667/) (2023)
- [Masked Autoencoders Enable Efficient Knowledge Distillers](https://mlsanity.com/paper/2208.12256/) (2022)
- [Contrastive Feature Masking Open-Vocabulary Vision Transformer](https://mlsanity.com/paper/2309.00775/) (2023)
- [Multi-Label Guided Soft Contrastive Learning for Efficient Earth Observation Pretraining](https://mlsanity.com/paper/2405.20462/) (2024)
- [Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models](https://mlsanity.com/paper/2305.08776/) (2023)
- [Event Camera Data Dense Pre-training](https://mlsanity.com/paper/2311.11533/) (2023)
- [Self-supervised video pretraining yields robust and more human-aligned visual representations](https://mlsanity.com/paper/2210.06433/) (2022)
- [Multi-Label Self-Supervised Learning with Scene Images](https://mlsanity.com/paper/2308.03286/) (2023)
- [CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception](https://mlsanity.com/paper/2306.00349/) (2023)
- [Semantic-Aware Fine-Grained Correspondence](https://mlsanity.com/paper/2207.10456/) (2022)
- [R-MAE: Regions Meet Masked Autoencoders](https://mlsanity.com/paper/2306.05411/) (2023)
- [Refining CLIP's Spatial Awareness: A Visual-Centric Perspective](https://mlsanity.com/paper/2504.02328/) (2025)
- [Correlational Image Modeling for Self-Supervised Visual Pre-Training](https://mlsanity.com/paper/2303.12670/) (2023)
- [Region-centric Image-Language Pretraining for Open-Vocabulary Detection](https://mlsanity.com/paper/2310.00161/) (2023)
- [Coarse Is Better? A New Pipeline Towards Self-Supervised Learning with Uncurated Images](https://mlsanity.com/paper/2306.04244/) (2023)
- [A Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning](https://mlsanity.com/paper/2503.06960/) (2025)
- [DenseDINO: Boosting Dense Self-Supervised Learning with Token-Based Point-Level Consistency](https://mlsanity.com/paper/2306.04654/) (2023)
- [Pixel-Wise Contrastive Distillation](https://mlsanity.com/paper/2211.00218/) (2022)
- [Exploring Transformers for Open-world Instance Segmentation](https://mlsanity.com/paper/2308.04206/) (2023)
- [GCL: Gradient-Guided Contrastive Learning for Medical Image Segmentation with Multi-Perspective Meta Labels](https://mlsanity.com/paper/2309.08888/) (2023)
- [Pixel-level Correspondence for Self-Supervised Learning from Video](https://mlsanity.com/paper/2207.03866/) (2022)
- [A Study on Self-Supervised Object Detection Pretraining](https://mlsanity.com/paper/2207.04186/) (2022)
- [De-coupling and De-positioning Dense Self-supervised Learning](https://mlsanity.com/paper/2303.16947/) (2023)
- [Localized Region Contrast for Enhancing Self-Supervised Learning in Medical Image Segmentation](https://mlsanity.com/paper/2304.03406/) (2023)
- [ContrastMotion: Self-supervised Scene Motion Learning for Large-Scale LiDAR Point Clouds](https://mlsanity.com/paper/2304.12589/) (2023)
- [Box-based Refinement for Weakly Supervised and Unsupervised Localization Tasks](https://mlsanity.com/paper/2309.03874/) (2023)
- [Cohere3D: Exploiting Temporal Coherence for Unsupervised Representation Learning of Vision-based Autonomous Driving](https://mlsanity.com/paper/2402.15583/) (2024)

## Abstract (arXiv)

In this work we present point-level region contrast, a self-supervised pre-training approach for the task of object detection. This approach is motivated by the two key factors in detection: localization and recognition. While accurate localization favors models that operate at the pixel- or point-level, correct recognition typically relies on a more holistic, region-level view of objects. Incorporating this perspective in pre-training, our approach performs contrastive learning by directly sampling individual point pairs from different regions. Compared to an aggregated representation per region, our approach is more robust to the change in input region quality, and further enables us to implicitly improve initial region assignments via online knowledge distillation during training. Both advantages are important when dealing with imperfect regions encountered in the unsupervised setting. Experiments show point-level region contrast improves on state-of-the-art pre-training methods for object detection and segmentation across multiple tasks and datasets, and we provide extensive ablation studies and visualizations to aid understanding. Code will be made available.