sabyasachis · January 25, 2020 07:41
diff --git a/small_large_filter_compare.csv b/small_large_filter_compare.csv
	Smaller Filter Sizes	Larger Filter Sizes
	It has a smaller receptive field as it looks at very few pixels at once.	Larger receptive field per layer.
	Highly local features extracted without much image overview.	Quite generic features extracted spread across the image.
	Therefore captures smaller, complex features in the image.	Therefore captures the basic components in the image.
	Amount of information extracted will be vast, maybe useful in later layers.	Amount of information extracted are considerably lesser.
	Slow reduction in the image dimension can make the network deep	Fast reduction in the image dimension makes the network shallow
	Better weight sharing	Poorer weight sharing
	In an extreme scenario, using a 1x1 convolution is like treating each pixel as a useful feature.	Using a image sized filter is equivalent to a fully connected layer.