From 35bcf69196d1b466b83866fc07d53742785b2ba6 Mon Sep 17 00:00:00 2001 From: roman807 Date: Tue, 19 Mar 2024 11:41:11 +0100 Subject: [PATCH] Update readme with disclaimer (#316) * updated readme * typo * update landing page --- docs/index.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/index.md b/docs/index.md index 07836c65..d0f5d826 100644 --- a/docs/index.md +++ b/docs/index.md @@ -88,9 +88,9 @@ For more details on the FM-backbones and instructions to replicate the results, ## Evaluation setup -With the FM, *eva* computes embeddings for all WSI patches which are then used as input to train a downstream head consisting of a single linear layer in a supervised setup for each of the benchmark datasets. +*Note that the current version of eva implements the task- & model-independent and fixed default set up following the standard evaluation protocol proposed by [1] and described in the table below. We selected this approach to prioritize reliable, robust and fair FM-evaluation while being in line with common literature. Additionally, with future versions we are planning to allow the use of cross-validation and hyper-parameter tuning to find the optimal setup to achieve best possible performance on the implemented downstream tasks.* -To standardize evaluations, the default configurations *eva* uses are based on the evaluation protocol proposed by [1] and dataset/task specific characteristics. We use early stopping with a patience of 5% of the maximal number of epochs. +With the FM as input, *eva* computes embeddings for all WSI patches which are then used as input to train a downstream head consisting of a single linear layer in a supervised setup for each of the benchmark datasets. We use early stopping with a patience of 5% of the maximal number of epochs. | | | |-------------------------|---------------------------|