Self-EMD: Self-Supervised Object Detection without ImageNet
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Objectobject-detectionObject DetectionRepresentation LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Self-Supervised Object Detection via Generative Image Synthesis
We present SSOD, the first end-to-end analysis-by synthesis framework with controllable GANs for the task of self-supervised object detection. We use collections of real world images without bounding box annotations to l…
Image GenerationObjectobject-detectionObject DetectionHASSOD: Hierarchical Adaptive Self-Supervised Object Detection
The human visual perception system demonstrates exceptional capabilities in learning without explicit supervision and understanding the part-to-whole composition of objects. Drawing inspiration from these two abilities, …
Objectobject-detectionObject DetectionSelf-Supervised LearningTowards Unsupervised Object Detection From LiDAR Point Clouds
In this paper, we study the problem of unsupervised object detection from 3D point clouds in self-driving scenes. We present a simple yet effective method that exploits (i) point clustering in near-range areas where the …
Objectobject-detectionObject DetectionObject Discovery+1Self-supervised object detection from audio-visual correspondence
We tackle the problem of learning object detectors without supervision. Differently from weakly-supervised object detection, we do not assume image-level class labels. Instead, we extract a supervisory signal from audio-…
Objectobject-detectionObject DetectionSound Source Localization+1Self-Supervised Representation Learning for Visual Anomaly Detection
Self-supervised learning allows for better utilization of unlabelled data. The feature representation obtained by self-supervision can be used in downstream tasks such as classification, object detection, segmentation, a…
Anomaly DetectionGeneral Classificationobject-detectionObject Detection+4