Loading
Attention-based multiple-instance learning gives each tile of a slide a learned weight and sums the weighted tile vectors into one slide vector, so a slide-level label can train the model and the weights show which regions mattered.
In multiple-instance learning the learner receives labelled bags of instances rather than labelled instances (Wikipedia). Ilse, Tomczak and Welling proposed pooling the instances with a small attention network, and Lu and colleagues' CLAM applied it to whole-slide images with clustering constraints for data-efficient, weakly supervised pathology. It is the default slide encoder head over frozen tile embeddings, the interface most pathology pipelines expose, and its attention maps are read as heat maps of evidence.
Shares Tile and patch encoding of slides, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Tile and patch encoding of slides, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Transformer and attention, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Transformer and attention, Pathology foundation models: UNI, UNI2, Virchow2, CTransPath, CONCH, TITAN, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Transformer and attention, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Pathology foundation models: UNI, UNI2, Virchow2, CTransPath, CONCH, TITAN, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Transformer and attention, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Tile and patch encoding of slides, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.