From a1ae56733572be5505866fb8d8d255f2e0ca87f7 Mon Sep 17 00:00:00 2001 From: shihy Date: Wed, 27 Dec 2023 22:38:50 +0800 Subject: [PATCH] [DOC] Modify readme.md for Image Example --- examples/dataset_image_workflow/README.md | 8 +++++--- 1 file changed, 5 insertions(+), 3 deletions(-) diff --git a/examples/dataset_image_workflow/README.md b/examples/dataset_image_workflow/README.md index 6f6161f..c1f6ff9 100644 --- a/examples/dataset_image_workflow/README.md +++ b/examples/dataset_image_workflow/README.md @@ -37,10 +37,12 @@ With the experimental setup above, we evaluated the performance of RKME Image by | Job Selector Reuse (Multiple) | 0.534 | | Average Ensemble Reuse (Multiple) | 0.676 | -In some specific settings, the user will have a small number of labeled samples. In such settings, learning the weight of selected learnwares on a limited number of labeled samples can result in a better performance than training directly on a limited number of labeled samples. - ### Labelled Sample Scenario +In some specific settings, the user will have a small number of labeled samples. In such settings, learning the weight of selected learnwares on a limited number of labeled samples can result in a better performance than training directly on a limited number of labeled samples. +
Results on Image Experimental Scenario -
\ No newline at end of file + + +Note that in labelled sample scenario, the labelled samples are repeatedly sampled 3 to 10 times, in order to reduce the estimation error in accuracy due to random sampling. \ No newline at end of file