K-convexity Shape Priors for Segmentation

Isack, Hossam; Gorelick, Lena; Ng, Karin; Veksler, Olga; Boykov, Yuri

doi:10.1007/978-3-030-01252-6_3

Cited by 12 publications

(8 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this paper, we consider a convexity-constrained Dubins model defined, in view of (21), by the curvature penalty function…”

Section: Convex-constrained Dubins Car Modelmentioning

confidence: 99%

“…The hedgehog-like shape prior [20] generalizes the geodesic star convexity constraint [19] to enlarge the applicable scope of the original case. Isack et al [21] proposed a flexible k-convexity prior-based segmentation model which allows overlaps between different regions. However, these graph-based approaches with convexity constraint did not consider the curvature regularization.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Geodesic Models with Convexity Shape Prior

Chen,

Mirebeau,

Shu

et al. 2021

Preprint

View full text Add to dashboard Cite

The minimal geodesic models based on the Eikonal equations are capable of finding suitable solutions in various image segmentation scenarios. Existing geodesic-based segmentation approaches usually exploit image features in conjunction with geometric regularization terms, such as Euclidean curve length or curvature-penalized length, for computing geodesic curves. In this paper, we take into account a more complicated problem: finding curvature-penalized geodesic paths with a convexity shape prior. We establish new geodesic models relying on the strategy of orientation-lifting, by which a planar curve can be mapped to an high-dimensional orientation-dependent space. The convexity shape prior serves as a constraint for the construction of local geodesic metrics encoding a particular curvature constraint. Then the geodesic distances and the corresponding closed geodesic paths in the orientation-lifted space can be efficiently computed through state-of-the-art Hamiltonian fast marching method. In addition, we apply the proposed geodesic models to the active contours, leading to efficient interactive image segmentation algorithms that preserve the advantages of convexity shape prior and curvature penalization.

show abstract

“…In this paper, we consider a convexity-constrained Dubins model defined, in view of (21), by the curvature penalty function…”

Section: Convex-constrained Dubins Car Modelmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Geodesic Models with Convexity Shape Prior

Chen,

Mirebeau,

Shu

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Moreover, there are many other regularization terms going beyond the basic first-order smoothness (boundary length) enforced by the Potts term in (1). The extensions include curvature [57,47,46], Pn-Potts [31], convexity [25,26], etc.…”

Section: Regularized Energies In Low-level Segmentationmentioning

confidence: 99%

Robust Trust Region for Weakly Supervised Segmentation

Marin¹,

Boykov²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Acquisition of training data for the standard semantic segmentation is expensive if requiring that each pixel is labeled. Yet, current methods significantly deteriorate in weakly supervised settings, e.g. where a fraction of pixels is labeled or when only image-level tags are available. It has been shown that regularized losses-originally developed for unsupervised low-level segmentation and representing geometric priors on pixel labels-can considerably improve the quality of weakly supervised training. However, many common priors require optimization stronger than gradient descent. Thus, such regularizers have limited applicability in deep learning. We propose a new robust trust region approach for regularized losses improving the state-of-the-art results. Our approach can be seen as a higher-order generalization of the classic chain rule. It allows neural network optimization to use strong low-level solvers for the corresponding regularizers, including discrete ones.

show abstract

“…Recently, Isack et al [32] introduce the notion of Kconvexity, and demonstrated its application in translucent instance segmentation via an energy minimization on an MRF. This allows enforcing a convexity prior on the shape of an instance (such as star [33], geodesic-star [34], hedgehog [35], or regular [36]).…”

Section: Related Workmentioning

confidence: 99%

Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation

Jang,

Wei,

Zhang

et al. 2020

Preprint

View full text Add to dashboard Cite

Blastomere instance segmentation is important for analyzing embryos' abnormality. To measure the accurate shapes and sizes of blastomeres, their amodal segmentation is necessary. Amodal instance segmentation aims to recover the complete silhouette of an object even when the object is not fully visible. For each detected object, previous methods directly regress the target mask from input features. However, images of an object under different amounts of occlusion should have the same amodal mask output, which makes it harder to train the regression model. To alleviate the problem, we propose to classify input features into intermediate shape codes and recover complete object shapes from them. First, we pre-train the Vector Quantized Variational Autoencoder (VQ-VAE) model to learn these discrete shape codes from ground truth amodal masks. Then, we incorporate the VQ-VAE model into the amodal instance segmentation pipeline with an additional refinement module. We also detect an occlusion map to integrate occlusion information with a backbone feature. As such, our network faithfully detects bounding boxes of amodal objects. On an internal embryo cell image benchmark, the proposed method outperforms previous state-of-the-art methods. To show generalizability, we show segmentation results on the public KINS natural image benchmark. To examine the learned shape codes and model design choices, we perform ablation studies on a synthetic dataset of simple overlaid shapes. Our method would enable accurate measurement of blastomeres in in vitro fertilization (IVF) clinics, which potentially can increase IVF success rate.

show abstract

K-convexity Shape Priors for Segmentation

Cited by 12 publications

References 24 publications

Geodesic Models with Convexity Shape Prior

Geodesic Models with Convexity Shape Prior

Robust Trust Region for Weakly Supervised Segmentation

Learning Vector Quantized Shape Code for Amodal Blastomere Instance Segmentation

Contact Info

Product

Resources

About