From fa9747d9a12bde6b2bf5fd5edaf0c801b1dfac00 Mon Sep 17 00:00:00 2001 From: Jim Martens Date: Thu, 14 Feb 2019 11:13:40 +0100 Subject: [PATCH] Fixed formatting --- Home.md | 1 + 1 file changed, 1 insertion(+) diff --git a/Home.md b/Home.md index 337c929..55ddca2 100644 --- a/Home.md +++ b/Home.md @@ -4,6 +4,7 @@ Explanation: detecting when an object detector fails by producing a prediction "this bounding box has object of class X", where in fact the object is of class Y which has not been encountered during training. **Baseline**: "Dropout Sampling for Robust Object Detection in Open-Set Conditions", Miller et al., ICRA 2018 + **Abstract**: They apply the SSD network as a starting point. The method they propose essentially consists of 1) enabling dropout during forward pass also and 2) feeding the same image through SSD multiple time (with dropout on, so result will be different each time!), and 3) filtering the resulting bounding boxes to detect the errors of the problem type. **Problem of baseline**: multiple forward passes can get rather wasteful in terms of required computation time (they need up to 20 per image)