> ML_LITERATURE // KIRILLOV-2023-SEGMENT-ANYTHING-FOUNDATION-MODEL_v1.0
Segment Anything (SAM)
Alexander Kirillov, Eric Mintun, Nikhila Ravi, Hanzi Mao, Chloe Rolland, Laura Gustafson, Tete Xiao, Spencer Whitehead, Alexander C. Berg, Wan-Yen Lo, Piotr Dollár, Ross Girshick · IEEE International Conference on Computer Vision (ICCV) (2023)
seminal-architecture2023industry-standardthirdPartyReproduced
Principal Contribution
Built the SA-1B dataset (11M images, 1.1B masks) and promptable Vision Transformer architecture enabling zero-shot interactive object segmentation from points, boxes, or text.
Operational Relevance
Directly guides architectural decisions, alignment strategy, and serving infrastructure for task-image-segmentation.
Assumptions
- Empirical distribution regularity holds and target domain adheres to pretraining linguistic/visual support
Limitations
- Resource scaling, inference memory requirements, and alignment robustness vary with model size and hardware topology
Connected Algorithms, Architectures & Tools
Related Algorithms:
Related Architectures:
Implementing Libraries: