From 7251dfc0d6d62dbaa60a5faaab2f5c3643596a5e Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Wed, 25 Sep 2019 13:23:13 +0200 Subject: [PATCH] Fixed explanation of averaging Signed-off-by: Jim Martens --- body.tex | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/body.tex b/body.tex index c28b9b5..d8635bd 100644 --- a/body.tex +++ b/body.tex @@ -927,8 +927,8 @@ This behaviour is caused by a large imbalance of detections between the classes. For vanilla SSD with 0.2 confidence threshold there are a total of 36,863 detections after non-maximum suppression and top \(k\). The persons class contributes 14,640 detections or around 40\% to that number. Another strong class is cars with 2,252 detections or around -6\%. This means that two classes have together almost as many detections -as the remaining 58 classes combined. +6\%. In third place come chairs with 1352 detections or around 4\%. This means that three classes have together roughly as many detections +as the remaining 57 classes combined. In macro averaging, the cumulative precision and recall values are calculated per class and then averaged across all classes. Smaller