Table 7.

Segmentation and recognition using crisp region proposals of materials (OS) and things & stuff (MSRC)

Dataset	Measure (%)	VGG-M			VGG-VD
		FC-CNN	FV-CNN	FV+FC-CNN	FC-CNN	FV-CNN	FC+FV-CNN	CRF	SoA
OS	pp-acc	36.0	48.6 (46.9)	49.8	38.5	55.5 (55.7)	55.9	56.5	–
OSA	acc-osa (2)	42.8	66.0	63.4	42.1	67.9	64.6	68.9	–
MSRC	acc-msrc (3)	56.1	82.3	75.2	57.7	86.9	81.5	90.2	86.5 Ladicky et al. (2010)

Per-pixel accuracies are reported, using the MSRC variant (see text) for the MSRC dataset. Results using MCG proposals (Arbeláez et al. 2014) are reported in brackets for FV-CNN