Deep Extreme Cut: From Extreme Points to Object Segmentation

Maninis, Kevis-Kokitsi; Caelles, Sergi; Pont-Tuset, Jordi; Gool, Luc Van

doi:10.1109/cvpr.2018.00071

Cited by 376 publications

(427 citation statements)

References 40 publications

Supporting

Mentioning

419

Contrasting

Unclassified

Order By: Relevance

“…This is especially tricky to do for threedimensional objects where the user typically has to navigate three multi-planar reformatted views (axial, coronal, sagittal) in order to achieve the task. Recent studies have also shown the time savings using extreme point selection brings for 2D object selection instead of traditional bounding box selection [16,17]. At the same time, extreme points provide additional information to the segmentation model (which can be observed in our experimental section, Table 1.…”

Section: Extreme Point Selectionmentioning

confidence: 61%

See 1 more Smart Citation

Weakly Supervised Segmentation from Extreme Points

Roth

Zhang

Yang

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Annotation of medical images has been a major bottleneck for the development of accurate and robust machine learning models. Annotation is costly and time-consuming and typically requires expert knowledge, especially in the medical domain. Here, we propose to use minimal user interaction in the form of extreme point clicks in order to train a segmentation model that can, in turn, be used to speed up the annotation of medical images. We use extreme points in each dimension of a 3D medical image to constrain an initial segmentation based on the random walker algorithm. This segmentation is then used as a weak supervisory signal to train a fully convolutional network that can segment the organ of interest based on the provided user clicks. We show that the network's predictions can be refined through several iterations of training and prediction using the same weakly annotated data. Ultimately, our method has the potential to speed up the generation process of new training datasets for the development of new machine learning and deep learning-based models for, but not exclusively, medical image analysis.

show abstract

Section: Extreme Point Selectionmentioning

confidence: 61%

“…This extra channel includes 3D Gaussians G centered on each point location clicked by the user. This approach is similar to [16] but here we extended it to 3D medical imaging problems. Figure 1 illustrates our approach.…”

Section: Extreme Point Selectionmentioning

confidence: 99%

Weakly Supervised Segmentation from Extreme Points

Roth

Zhang

Yang

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…Interactive Segmentation. Recent advances in interactive segmentation (e.g., [1,38,2]) utilize neural networks to convert sparse human inputs into high quality segments. For novel domains without large-scale training data, blockannotated images can act as cost-efficient seed data to train these models.…”

Section: Compatibility With Existing Annotation Methodsmentioning

confidence: 99%

“…Matting and object selection [50,33,34,6,58,57,10,30,59] generate tight boundaries from loosely annotated boundaries or few inside/outside clicks and scribbles. [44,38] introduced a predictive method which automatically infers a foreground mask from 4 boundary clicks, and was extended to full-image segmentation in [2]. The number of boundary clicks was further reduced to as few as one by [1].…”

Section: Related Workmentioning

confidence: 99%

Block Annotation: Better Image Annotation With Sub-Image Decomposition

Lin

Upchurch

Bala

2019

2019 IEEE/CVF International Conference on Computer Vision (ICCV)

View full text Add to dashboard Cite

Image datasets with high-quality pixel-level annotations are valuable for semantic segmentation: labelling every pixel in an image ensures that rare classes and small objects are annotated. However, full-image annotations are expensive, with experts spending up to 90 minutes per image. We propose block sub-image annotation as a replacement for full-image annotation. Despite the attention cost of frequent task switching, we find that block annotations can be crowdsourced at higher quality compared to full-image annotation with equal monetary cost using existing annotation tools developed for full-image annotation. Surprisingly, we find that 50% pixels annotated with blocks allows semantic segmentation to achieve equivalent performance to 100% pixels annotated. Furthermore, as little as 12% of pixels annotated allows performance as high as 98% of the performance with dense annotation. In weakly-supervised settings, block annotation outperforms existing methods by 3-4% (absolute) given equivalent annotation time. To recover the necessary global structure for applications such as characterizing spatial context and affordance relationships, we propose an effective method to inpaint block-annotated images with high-quality labels without additional human effort. As such, fewer annotations can also be used for these applications compared to full-image annotation.

show abstract

“…Contrary to the two stream approach, deep extreme cut [138] takes a single pipeline to create segmentation maps from RGB Images. This method expects 4 points from the user denoting the four extreme regions in the boundary of the object (leftmost, rightmost, topmost,bottommost).…”

Section: Deep Extreme Cutmentioning

confidence: 99%

Understanding Deep Learning Techniques for Image Segmentation

et al. 2019

View full text Add to dashboard Cite

The machine learning community has been overwhelmed by a plethora of deep learning based approaches. Many challenging computer vision tasks such as detection, localization, recognition and segmentation of objects in unconstrained environment are being efficiently addressed by various types of deep neural networks like convolutional neural networks, recurrent networks, adversarial networks, autoencoders and so on. While there have been plenty of analytical studies regarding the object detection or recognition domain, many new deep learning techniques have surfaced with respect to image segmentation techniques. This paper approaches these various deep learning techniques of image segmentation from an analytical perspective. The main goal of this work is to provide an intuitive understanding of the major techniques that has made significant contribution to the image segmentation domain. Starting from some of the traditional image segmentation approaches, the paper progresses describing the effect deep learning had on the image segmentation domain. Thereafter, most of the major segmentation algorithms have been logically categorized with paragraphs dedicated to their unique contribution. With an ample amount of intuitive explanations, the reader is expected to have an improved ability to visualize the internal dynamics of these processes.

show abstract

Deep Extreme Cut: From Extreme Points to Object Segmentation

Cited by 376 publications

References 40 publications

Weakly Supervised Segmentation from Extreme Points

Weakly Supervised Segmentation from Extreme Points

Block Annotation: Better Image Annotation With Sub-Image Decomposition

Understanding Deep Learning Techniques for Image Segmentation

Contact Info

Product

Resources

About