Self-EMD: Self-Supervised Object Detection without ImageNet

2020/11/27 by Songtao Liu, Liu, Songtao, Zeming Li +3 · 9 citations
Computer Science · #Advanced Image and Video Retrieval Techniques #Advanced Neural Network Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Video Surveillance and Tracking Methods #cs.CV

paper · pdf · doi:10.48550/arxiv.2011.13677

openalex publication_date 2020/11/27 · arxiv created 2021/03/22 · arxiv updated 2021/03/23 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• The Pascal Visual Object Classes (VOC) Challenge
• ImageNet Large Scale Visual Recognition Challenge
• The Earth Mover's Distance as a Metric for Image Retrieval
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal\n Networks
• A Simple Framework for Contrastive Learning of Visual Representations
• Improved Baselines with Momentum Contrastive Learning
• Bootstrap your own latent: A new approach to self-supervised Learning
• Momentum Contrast for Unsupervised Visual Representation Learning
• Unsupervised Learning of Visual Features by Contrasting Cluster Assignments

Cited by

• UNIV: Unified Foundation Model for Infrared and Visible Modalities
• Beyond Instance Consistency: Investigating View Diversity in Self-supervised Learning
• Aligning Pretraining for Detection via Object-Level Contrastive Learning
• Multiple Object Stitching for Unsupervised Representation Learning
• A Contrastive Learning Foundation Model Based on Perfectly Aligned Sample Pairs for Remote Sensing Images
• Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
• Self-supervised Learning of 3D Object Understanding by Data Association and Landmark Estimation for Image Sequence
• MST: Masked Self-Supervised Transformer for Visual Representation
• RADLER: Radar Object Detection Leveraging Semantic 3D City Models and Self-Supervised Radar-Image Learning

Related

• Object discovery and representation networks
• Self-Supervised Learning for Real-World Object Detection: a Survey
• UniVIP: A Unified Framework for Self-Supervised Visual Pre-training
• EMP-SSL: Towards Self-Supervised Learning in One Training Epoch
• Object Detection from Scratch with Deep Supervision