Visual Learning and Recognition: Difference between revisions

Visual Learning and Recognition (view source)

603 bytes added , 22 October 2020

5,337

edits

@@ Line 663: / Line 663: @@
 ===Homework===
-Read OHEM paper.
+Read [https://arxiv.org/pdf/1604.03540.pdf OHEM paper].
+Summary of online hard example mining:
+Previously hard mining involved the following two steps
+# Freeze the model and run it on 10-100s to find hard examples.
+# Train on hard examples.
+They instead propose finding hard-examples per mini-batch.
+This is possible because there are thousands of RoIs within each image.
+# Run a mini-batch through the CNN feature extractor.
+# Do forward-pass on all RoIs.
+# Sort RoIs by loss and take the top <math>B/N</math> examples.
+#* Filter duplicates using NMS.
+# Backwards pass only on the top <math>B/N</math> examples.
 ==Will be on the exam==