@@ -40,7 +40,7 @@
Summary
Metadata (more detail below)
- This benchmarking tool features the MILK10k training dataset (5,240 lesions) and a blind
+ This benchmark features the MILK10k training dataset (5,240 lesions) and a blind
held-out test dataset (479 lesions) called the MILK10k Benchmark.
@@ -174,7 +174,7 @@
Datasets
- This benchmarking tool features the MILK10k Benchmark dataset, comprising 958 images —
+ This benchmark features the MILK10k Benchmark dataset, comprising 958 images —
specifically, close-up and dermatoscopic image pairs for 479 skin lesions. The benchmark
dataset originates from the same sources as the original
MILK10k and covers the same eleven