Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications

Levinkov, Evgeny; Uhrig, Jonas; Tang, Siyu; Omran, Mohamed M.; Insafutdinov, Eldar; Kirillov, Alexander M.; Rother, Carsten; Brox, Thomas; Schiele, Bernt; Andres, Bjoern

doi:10.48550/arxiv.1611.04399

Cited by 2 publications

(2 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The problem related to (5)-( 8) was considered in [31] for foreground/background segmentation. Although the problem ( 5)-( 8) is NP-hard and it contains a lot of hard constraints, there exists an efficient approximate solver for it [32], which we used in our experiments. For solving the problem over 3000 nodes (superpixels) and 9 labels (segment classes) it required less than a second on average.…”

Section: Image Partitionmentioning

confidence: 99%

InstanceCut: From Edges to Instances with MultiCut

Kirillov

Levinkov

Andres

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

239

143

View full text Add to dashboard Cite

This work addresses the task of instance-aware semantic segmentation. Our key motivation is to design a simple method with a new modelling-paradigm, which therefore has a different trade-off between advantages and disadvantages compared to known approaches. Our approach, we term InstanceCut, represents the problem by two output modalities: (i) an instance-agnostic semantic segmentation and (ii) all instance-boundaries. The former is computed from a standard convolutional neural network for semantic segmentation, and the latter is derived from a new instanceaware edge detection model. To reason globally about the optimal partitioning of an image into instances, we combine these two modalities into a novel MultiCut formulation. We evaluate our approach on the challenging CityScapes dataset. Despite the conceptual simplicity of our approach, we achieve the best result among all published methods, and perform particularly well for rare object classes.

show abstract

Section: Image Partitionmentioning

confidence: 99%

InstanceCut: From Edges to Instances with MultiCut

Kirillov

Levinkov

Andres

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

Self Cite

239

143

View full text Add to dashboard Cite

show abstract

“…The problem is solved using a series of K bipartite graph matching problems, each solved using the Hungarian algorithm [8]. In [9], the graph partitioning problem formulated in DeeperCut [2] is solved quickly using a modified KL algorithm [10], instead of ILP. Similar to our approach, [9] reduces the complexity of the graphpartitioning problem by considering only a subset of pairwise associations between different body parts.…”

Section: Related Workmentioning

confidence: 99%

A Greedy Part Assignment Algorithm for Real-Time Multi-person 2D Pose Estimation

Varadarajan

Datta

Tickoo

2018

2018 IEEE Winter Conference on Applications of Computer Vision (WACV)

View full text Add to dashboard Cite

Human pose-estimation in a multi-person image involves detection of various body parts and grouping them into individual person clusters. While the former task is challenging due to mutual occlusions, the combinatorial complexity of the latter task is very high. We propose a greedy part assignment algorithm that exploits the inherent structure of the human body to achieve a lower complexity, compared to any of the prior published works. This is accomplished by (i) reducing the number of partcandidates using the estimated number of people in the image, (ii) doing a greedy sequential assignment of partclasses, following the kinematic chain from head to ankle (iii) doing a greedy assignment of parts in each part-class set, to person-clusters (iv) limiting the candidate person clusters to the most proximal clusters using human anthropometric data and (v) using only a specific subset of pre-assigned parts for establishing pairwise structural constraints. We show that, these steps sparsify the bodyparts relationship graph and reduces the algorithm's complexity to be linear in the number of candidates of any single part-class. We also propose methods for improving the accuracy of pose-estimation by (i) spawning personclusters from any unassigned significant body part and (ii) suppressing hallucinated parts. On the MPII multi-person pose database, pose-estimation using the proposed method takes only 0.14 seconds per image. We show that, our proposed algorithm, by using a large spatial and structural context, achieves the state-of-the-art accuracy on both MPII and WAF multi-person pose datasets, demonstrating the robustness of our approach.

show abstract

Joint Graph Decomposition and Node Labeling: Problem, Algorithms, Applications

Cited by 2 publications

References 0 publications

InstanceCut: From Edges to Instances with MultiCut

InstanceCut: From Edges to Instances with MultiCut

A Greedy Part Assignment Algorithm for Real-Time Multi-person 2D Pose Estimation

Contact Info

Product

Resources

About