השוואת שיטות

	פילוח מופעים מפוקח-בקושי	פילוח מופעים בלמידה עצמית (Self-supervised Instance Segmentation)
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2015–2019	2021–2022
הוגה השיטה	Multiple contributors (e.g., Hsu et al., Khoreva et al.)	Wang et al. (FreeSOLO); Caron et al. (DINO)
סוג	Weakly supervised deep learning for pixel-wise instance delineation	Self-supervised deep learning for pixel-level object delineation
מקור מכונן	Hsu, C.-C., Hsu, K.-J., Tsai, C.-C., Lin, Y.-Y., & Chuang, Y.-Y. (2019). Weakly supervised instance segmentation using the bounding box tightness prior. Advances in Neural Information Processing Systems (NeurIPS), 32.	Wang, X., Zhu, Z., Cao, G., Yao, Z., Jiang, Z., & Ye, J. (2022). FreeSOLO: Learning to Segment Objects without Annotations. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 14176–14186.
כינויים	WSIS, weakly-supervised mask prediction, weak-label instance segmentation, box-supervised instance segmentation	SSIS, unsupervised instance segmentation, label-free instance segmentation, self-supervised mask prediction
קשורות	6	4
תקציר	Weakly supervised instance segmentation trains deep networks to delineate individual object instances at pixel level using only cheap, incomplete annotations — such as bounding boxes, image-level labels, or point clicks — rather than costly full pixel-wise masks. It dramatically reduces annotation effort while still producing instance-level masks for each object in an image.	Self-supervised instance segmentation learns to detect and delineate individual object instances in images without any human-annotated masks or bounding boxes. Instead of relying on costly pixel-level labels, it exploits self-supervised pretraining, multi-view consistency, and pseudo-label generation to discover and segment objects purely from raw image data.