Scientific Reports

Table 3 Derivations on the compared models on the aforementioned datasets.

From: Scene categorization by Hessian-regularized active perceptual feature selection

Dataset	FWK	FTK	MRH	SP	LLC-SP	SC-SP	OB-SP	SV	SSC
Scene-15	0.013	0.012	0.012	0.015	0.016	0.017	0.011	0.013	0.012
Scene-67	0.014	0.013	0.015	0.014	0.014	0.013	0.013	0.014	0.014
ZJU Aerial	0.014	0.015	0.016	0.015	0.016	0.015	0.014	0.013	0.014
ILSVRC-2010	0.014	0.013	0.013	0.013	0.014	0.013	0.012	0.013	0.014
SUN397	0.012	0.014	0.014	0.013	0.014	0.015	0.016	0.013	0.015
Places205	0.013	0.014	0.015	0.014	0.016	0.014	0.016	0.015	0.017
MSEI	0.015	0.011	0.015	0.013	0.009	0.012	0.013	0.014	0.013

Dataset	IN-CNN	R-CNN	M-CNN	DM-CNN	SPP-CNN	SP-S	SP-GBVS	SP-LDA	Mesnil
Scene-15	0.016	0.013	0.014	0.014	0.015	0.013	0.014	0.013	0.015
Scene-67	0.013	0.015	0.013	0.013	0.014	0.013	0.015	0.013	0.012
ZJU Aerial	0.013	0.014	0.015	0.014	0.013	0.014	0.013	0.016	0.014
ILSVRC-2010	0.015	0.013	0.014	0.013	0.015	0.018	0.013	0.015	0.012
SUN397	0.013	0.014	0.015	0.012	0.014	0.012	0.014	0.014	0.015
Places205	0.012	0.014	0.012	0.013	0.013	0.014	0.013	0.012	0.013
MSEI	0.014	0.012	0.014	0.012	0.014	0.015	0.012	0.017	0.015

Dataset	Xiao	Cong	Fast R-CNN	Faster R-CNN	Ours (MKL)	Ours (Softmax)
Scene-15	0.012	0.014	0.013	0.014	0.009	0.011
Scene-67	0.017	0.012	0.013	0.013	0.007	0.009
ZJU Aerial	0.014	0.013	0.014	0.012	0.008	0.007
ILSVRC-2010	0.013	0.013	0.014	0.011	0.009	0.007
SUN397	0.012	0.013	0.014	0.013	0.009	0.008
Places205	0.013	0.012	0.014	0.012	0.008	0.006
MSEI	0.014	0.011	0.015	0.014	0.006	0.009

Back to article page

Search

Advanced search

Quick links