PASCAL VOC Challenge performance evaluation and download server
Home | Leaderboard

Segmentation Results: VOC2010 ^BETA

Competition "comp5" (train on VOC2010 data)

This leaderboard shows only those submissions that have been marked as public, and so the displayed rankings should not be considered as definitive.

• The highest scoring entry in each column is shown in bold.
• Clicking on the blue arrow symbol () at the top of a column will order the submissions from high to low wrt performance on that column.
• Clicking on the orange arrow symbol () at the left hand side of a table will identify entries with performance equivalent to the selected submission. For each object class all entries equivalent to the selected submission are marked by orange highlighting.
• gray highlighting with double stars (**) indicate that equivalent entries are not available for this submission yet.

Entries equivalent to a selected submission are determined by bootstrapping the performance measure, and assessing if the differences between the selected submission and the others are not statistically significant (see sec 3.5 in VOC 2014 paper).

Average Precision (AP %)

		mean	aero plane	bicycle	bird	boat	bottle	bus	car	cat	chair	cow	dining table	dog	horse	motor bike	person	potted plant	sheep	sofa	train	tv/ monitor	submission date
	O2P_SVRSEGM_CPMC_CSI [?]	49.6	68.6	33.1	48.9	37.2	49.5	64.2	66.0	48.5	18.3	54.6	30.6	41.0	62.1	58.0	53.2	38.1	58.8	32.9	46.2	46.5	20-Nov-2012
	CVC_Harmony [?]	35.4	56.7	20.6	31.0	33.9	20.8	57.6	51.4	35.8	7.1	28.1	22.6	24.3	29.3	49.4	37.8	23.3	37.6	18.1	45.6	30.7	29-Aug-2010
	CVC_Harmony+Det [?]	40.1	58.3	23.1	39.0	37.8	36.4	63.2	62.4	31.9	9.1	36.8	24.6	29.4	37.5	60.6	44.9	30.1	36.8	19.4	44.1	35.9	30-Aug-2010
	Svr-Segm [?]	39.7	52.5	27.4	32.3	34.5	47.4	60.6	54.8	42.6	9.0	32.9	25.3	27.1	32.4	47.1	38.3	36.8	50.3	21.9	35.2	40.9	30-Aug-2010
	AHCRF [?]	30.3	31.0	18.8	19.5	23.9	31.3	53.5	45.3	24.4	8.2	31.0	16.4	15.8	27.3	48.1	31.1	31.0	27.5	19.8	34.8	26.4	30-Aug-2010
	LSVM-MDPM [?]	31.8	36.7	23.9	20.9	18.8	41.0	62.7	49.0	21.5	8.3	21.1	7.0	16.4	28.2	42.5	40.5	19.6	33.6	13.3	34.1	48.5	26-Aug-2010
	Bonn_FGT_Segm [?]	36.5	54.6	22.5	25.1	27.6	40.0	60.2	48.3	39.4	7.3	30.8	21.3	25.3	34.9	54.1	36.6	22.5	45.0	17.6	33.5	37.0	30-Aug-2010
	REGION-LABEL [?]	29.1	38.8	21.5	13.6	9.2	31.1	51.9	44.4	25.7	6.7	26.0	12.5	12.8	31.0	41.9	44.4	5.7	37.5	10.0	33.2	32.3	30-Aug-2010
	UC3M_Generative_Discriminative [?]	27.8	45.9	12.3	14.5	22.3	9.3	46.8	38.3	41.7	-	35.9	20.7	34.1	34.8	33.5	24.6	4.7	25.6	13.0	26.8	26.1	30-Aug-2010

Abbreviations

Title	Method	Affiliation	Contributors	Description	Date
Associative hierarchical CRF	AHCRF	Oxford Brookes University	Lubor Ladicky Christopher Russell Philip Torr	Associative hierarchical CRF with detectors and cooccurence. One pixel layer with dense feature boost potential, 6 segmentation with potentials based on histograms of features, detector potential based on part-based model sliding window detector, generatively trained cooccurence potential	2010-08-30 22:14:09
FG Detection, FG Tiling	Bonn_FGT_Segm	Univeristy of Bonn	João Carreira, Adrian Ion, Fuxin Li, Cristian Sminchisescu	- Detection on figure-ground segmentations; - Classification by detection; - Semantic segmentation on figure-ground tilings;	2010-08-30 23:08:18
Harmony Potentials	CVC_Harmony	Computer Vision Center - Universitat Autònoma de Barcelona	Josep Maria Gonfaus, Xavier Boix, Fahad Kahn, Joost van de Weijer, Andrew Bagdanov, Marco Pedersoli, Jordi Gonzàlez, Joan Serrat	Our submission is based on [1]. We use the CVC_flat classification submission as the observations for the global node. New Absolute Position Prior is added to the Superpixels Probabilities [1] Josep M. Gonfaus, Xavier Boix, Joost Van de Weijer, Andrew D. Bagdanov, Joan Serrat, and Jordi Gonzàlez, " Harmony Potentials for Joint Classification and Segmentation ", in Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, 2010.	2010-08-29 20:10:26
CVC_Harmony plus Detection Priors	CVC_Harmony+Det	Computer Vision Center - Universitat Autònoma de Barcelona	Josep Maria Gonfaus, Xavier Boix, Fahad Kahn, Joost van de Weijer, Andrew Bagdanov, Marco Pedersoli, Joan Serrat, Xavier Roca, Jordi Gonzàlez	Our submission is based on [1] and the previous submission "CVC_Harmony". Here we add the detection scores of [2] as location prior in the image. [1] J.M. Gonfaus, X. Boix, J. Van de Weijer, A. D. Bagdanov, J. Serrat, and J. Gonzàlez, "Harmony Potentials for Joint Classification and Segmentation", in CVPR 2010. [2] Felzenszwalb, Girshick, McAllester, Ramanan, "Object Detection with Discriminatively Trained Part Based Models", PAMI 2010	2010-08-30 23:52:37
LSVM Mixtures of deformable part models	LSVM-MDPM	University of Chicago and TTI-C	Pedro Felzenszwalb (UChicago), Ross Girshick (UChicago), David McAllester (TTI-C)	Our submission is based on an extension of [1,2]. Each model has 6 components with 8 parts. We associate a binary mask with each component to generate segmentations. The object detection models were trained from bounding boxes. The segmentation masks were trained from segmentations. [1] P. Felzenszwalb, R. Girshick, D. McAllester, D. Ramanan. Object Detection with Discriminatively Trained Part Based Models. PAMI 32(9), Sept 2010 [2] http://people.cs.uchicago.edu/~pff/latent-release4/	2010-08-26 04:07:34
O2P+SVRSEGM Regressor + Composite Statistical Inference	O2P_SVRSEGM_CPMC_CSI	(1) Georgia Institute of Technology (2) University of California - Berkeley (3) Amazon Inc. (4) Lund University	Fuxin Li (1), Joao Carreira (2), Guy Lebanon (3), Cristian Sminchisescu (4)	We utilize a novel probabilistic inference procedure, Composite Statisitcal Inference (CSI) [1], on semantic segmentation using predictions on overlapping figure-ground hypotheses. Regressor predictions on segment overlaps to the ground truth object are modelled as generated by the true overlap with the ground truth segment plus noise, parametrized on the unknown percentage of each superpixel that belongs to the unknown ground truth. A joint optimization on all the superpixels and all the categories is then performed in order to maximize the likelihood of the SVR predictions. The optimization has a tight convex relaxation so solutions can be expected to be close to the global optimum. A fast and optimal search algorithm is then applied to retrieve each object. CSI takes the intuition from the SVRSEGM inference algorithm that multiple predictions on similar segments can be combined to better consolidate the segment mask. But it fully develops the idea by constructing a probabilistic framework and performing maximum composite likelihood jointly on all segments and categories. Therefore it is able to consolidate better object boundaries and handle hard cases when objects interact closely and heavily occlude each other. For each image, we use 150 overlapping figure-ground hypotheses generated by the CPMC algorithm (Carreira and Sminchisescu, PAMI 2012), SVRSEGM results, and linear SVR predictions on them with the novel second order O2P features (Carreira, Caseiro, Batista, Sminchisescu, ECCV2012; see VOC12 entry BONN_CMBR_O2P_CPMC_LIN) as the input to the inference algorithm. [1] Fuxin Li, Joao Carreira, Guy Lebanon, Cristian Sminchisescu. Composite Statistical Inference for Semantic Segmentation. CVPR 2013.	2012-11-20 18:39:06
Optimizing regions and their labels	REGION-LABEL	Stanford University	M. Pawan Kumar, Stephen Gould, Haithem Turki, Dan Preston, Daphne Koller	The method groups pixels into regions and assigns the regions a unique semantic label simultaneously by minimizing a global energy function. Features used include those obtained from an object detector (deformable parts-based model) as well as a bag of SIFT words computed over the region. Inference as described in CVPR 2010, learning as described in ICCV 2009.	2010-08-30 18:13:43
Svr-Segm	Svr-Segm	University of Bonn	Joao Carreira, Fuxin Li, Adrian Ion, Cristian Sminchisescu	Support vector regression to multiple descriptors extracted on segmentations. Descriptors include SIFT, color SIFT and HOG on foreground and background. Post-processing to eliminate spurious detections and segmentations. The winning method of 2009 challenge.	2010-08-30 22:52:55
Combination of Generative Discriminative Methods	UC3M_Generative_Discriminative	Universidad Carlos III de Madrid	Iván González-Díaz, Fernando Díaz de María	Combination of Supervised Topic Models with SVM-based discriminative methods for concurrent image recognition and segmentation	2010-08-30 13:27:41