방법 비교
선택한 방법을 나란히 검토하세요. 서로 다른 행은 강조 표시됩니다.
| 미세 조정된 이미지 분류× | 객체 탐지× | |
|---|---|---|
| 분야 | 딥러닝 | 딥러닝 |
| 계열 | Machine learning | Machine learning |
| 기원 연도≠ | 2010–2014 | 2014–2016 |
| 창시자≠ | Yosinski, J. et al.; Pan, S. J. & Yang, Q. | Girshick, R. et al. (R-CNN); Redmon, J. et al. (YOLO) |
| 유형≠ | Transfer learning / fine-tuning | Supervised deep learning (region proposal or single-shot) |
| 원전≠ | Yosinski, J., Clune, J., Bengio, Y., & Lipson, H. (2014). How transferable are features in deep neural networks? Advances in Neural Information Processing Systems (NeurIPS), 27, 3320–3328. link ↗ | 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. DOI ↗ |
| 별칭 | fine-tuning for image recognition, transfer learning image classifier, pretrained CNN fine-tuning, domain-specific image classifier | visual object detection, image object localization, region-based object detection, bounding-box detection |
| 관련≠ | 5 | 3 |
| 요약≠ | Fine-tuned image classification adapts a large neural network pretrained on a broad image corpus (such as ImageNet) to a specific target domain by continuing training on labeled domain images. This approach achieves strong accuracy with far fewer target-domain samples than training from scratch, making it the dominant paradigm for applied computer vision tasks. | 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. |
| ScholarGate데이터셋 ↗ |
|
|