# Self-EMD: Self-Supervised Object Detection without ImageNet

arXiv: https://arxiv.org/abs/2011.13677 · HTML: https://mlsanity.com/paper/2011.13677/

## Key facts

- Cited by 70 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Nov 2020.

## Built on by (most cited first, 30 of 70)

- [SPot-the-Difference Self-Supervised Pre-training for Anomaly Detection and Segmentation](https://mlsanity.com/paper/2207.14315/) (2022)
- [CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion](https://mlsanity.com/paper/2210.10716/) (2022)
- [MST: Masked Self-Supervised Transformer for Visual Representation](https://mlsanity.com/paper/2106.05656/) (2021)
- [Aligning Pretraining for Detection via Object-Level Contrastive Learning](https://mlsanity.com/paper/2106.02637/) (2021)
- [Self-Supervised Learning of Object Parts for Semantic Segmentation](https://mlsanity.com/paper/2204.13101/) (2022)
- [Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training](https://mlsanity.com/paper/2308.09718/) (2023)
- [Siamese Image Modeling for Self-Supervised Vision Representation Learning](https://mlsanity.com/paper/2206.01204/) (2022)
- [Unsupervised Object-Level Representation Learning from Scene Images](https://mlsanity.com/paper/2106.11952/) (2021)
- [Self-Supervised Visual Representation Learning with Semantic Grouping](https://mlsanity.com/paper/2205.15288/) (2022)
- [Unsupervised Domain Adaptive 3D Detection with Multi-Level Consistency](https://mlsanity.com/paper/2107.11355/) (2021)
- [Do Different Tracking Tasks Require Different Appearance Models?](https://mlsanity.com/paper/2107.02156/) (2021)
- [Hyperbolic Contrastive Learning for Visual Representations beyond Objects](https://mlsanity.com/paper/2212.00653/) (2022)
- [Masked Scene Contrast: A Scalable Framework for Unsupervised 3D Representation Learning](https://mlsanity.com/paper/2303.14191/) (2023)
- [Understanding Masked Image Modeling via Learning Occlusion Invariant Feature](https://mlsanity.com/paper/2208.04164/) (2022)
- [CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding](https://mlsanity.com/paper/2304.09670/) (2023)
- [Point-Level Region Contrast for Object Detection Pre-Training](https://mlsanity.com/paper/2202.04639/) (2022)
- [Learning Super-Features for Image Retrieval](https://mlsanity.com/paper/2201.13182/) (2022)
- [Dense Learning based Semi-Supervised Object Detection](https://mlsanity.com/paper/2204.07300/) (2022)
- [UniVIP: A Unified Framework for Self-Supervised Visual Pre-training](https://mlsanity.com/paper/2203.06965/) (2022)
- [Versatile Multi-Modal Pre-Training for Human-Centric Perception](https://mlsanity.com/paper/2203.13815/) (2022)
- [GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding](https://mlsanity.com/paper/2403.09639/) (2024)
- [Object-Aware Cropping for Self-Supervised Learning](https://mlsanity.com/paper/2112.00319/) (2021)
- [CrOC: Cross-View Online Clustering for Dense Visual Representation Learning](https://mlsanity.com/paper/2303.13245/) (2023)
- [Partially Does It: Towards Scene-Level FG-SBIR with Partial Input](https://mlsanity.com/paper/2203.14804/) (2022)
- [Semantics Meets Temporal Correspondence: Self-supervised Object-centric Learning in Videos](https://mlsanity.com/paper/2308.09951/) (2023)
- [Multi-Label Self-Supervised Learning with Scene Images](https://mlsanity.com/paper/2308.03286/) (2023)
- [CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping](https://mlsanity.com/paper/2310.07855/) (2023)
- [Near, far: Patch-ordering enhances vision foundation models' scene understanding](https://mlsanity.com/paper/2408.11054/) (2024)
- [AlignDet: Aligning Pre-training and Fine-tuning in Object Detection](https://mlsanity.com/paper/2307.11077/) (2023)
- [Crowd-SAM: SAM as a Smart Annotator for Object Detection in Crowded Scenes](https://mlsanity.com/paper/2407.11464/) (2024)

## Abstract (arXiv)

In this paper, we propose a novel self-supervised representation learning method, Self-EMD, for object detection. Our method directly trained on unlabeled non-iconic image dataset like COCO, instead of commonly used iconic-object image dataset like ImageNet. We keep the convolutional feature maps as the image embedding to preserve spatial structures and adopt Earth Mover's Distance (EMD) to compute the similarity between two embeddings. Our Faster R-CNN (ResNet50-FPN) baseline achieves 39.8% mAP on COCO, which is on par with the state of the art self-supervised methods pre-trained on ImageNet. More importantly, it can be further improved to 40.4% mAP with more unlabeled images, showing its great potential for leveraging more easily obtained unlabeled data. Code will be made available.