Порівняння методів

	Самостійне навчання виявлення об'єктів	Виявлення об'єктів
Галузь	Глибоке навчання	Глибоке навчання
Родина	Machine learning	Machine learning
Рік появи	2019–2021	2014–2016
Автор методу	He et al. (MoCo); Caron et al. (DINO); Henaff et al. (DetCon)	Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO)
Тип	Self-supervised pre-training + supervised fine-tuning	Supervised deep learning (region proposal or single-shot)
Основоположне джерело	He, K., Fan, H., Wu, Y., Xie, S., & Girshick, R. (2020). Momentum Contrast for Unsupervised Visual Representation Learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 9729–9738.	Girshick, R., Donahue, J., Darrell, T., & Malik, J. (2014). Rich feature hierarchies for accurate object detection and semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 580–587.
Інші назви	SSL object detection, self-supervised detection, unsupervised pre-training for detection, contrastive pre-training for detection	visual object detection, image object localization, region-based object detection, bounding-box detection
Пов'язані	4	3
Підсумок	Self-supervised object detection uses unlabeled image data to pre-train a visual backbone through pretext tasks such as contrastive learning or masked image modeling, then fine-tunes the backbone with a detection head on a smaller labeled dataset. This approach dramatically reduces reliance on expensive bounding-box annotations while matching or approaching fully supervised detection performance.	Object detection is a computer vision task in which a deep neural network simultaneously locates and classifies every instance of one or more object categories within an image, producing a bounding box and a class label for each detected object. Modern detectors — from the R-CNN family to YOLO and DETR — achieve near-human accuracy at real-time speeds on standard benchmarks.