Self-EMD: Self-Supervised Object Detection without ImageNet
arXiv:2011.13677
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.
References in corpus (7)
- Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
- A Simple Framework for Contrastive Learning of Visual Representations
- Bootstrap your own latent: A new approach to self-supervised Learning
- Improved Baselines with Momentum Contrastive Learning
- Unsupervised Learning of Visual Features by Contrasting Cluster Assignments
- Rethinking ImageNet Pre-training
- Cheaper Pre-training Lunch: An Efficient Paradigm for Object Detection
Cited by in corpus (10)
- CMID: A Unified Self-Supervised Learning Framework for Remote Sensing Image Understanding
- Aligning Pretraining for Detection via Object-Level Contrastive Learning
- Do Different Tracking Tasks Require Different Appearance Models?
- MST: Masked Self-Supervised Transformer for Visual Representation
- Semantic-Aware Generation for Self-Supervised Visual Representation Learning
- Unsupervised Object-Level Representation Learning from Scene Images
- Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
- Object-Aware Cropping for Self-Supervised Learning
- A New Training Framework for Deep Neural Network
- Self-supervised Learning of 3D Object Understanding by Data Association and Landmark Estimation for Image Sequence