F-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

Sofiiuk, Konstantin; Petrov, Ilia A.; Barinova, Olga; Konushin, Anton

doi:10.1109/cvpr42600.2020.00865

Cited by 155 publications

(118 citation statements)

References 22 publications

Supporting

Mentioning

112

Contrasting

Order By: Relevance

“…It shows that deep learning methods may not automatically guarantee that the known pixels annotated by the trimap has the correct result. In fact, similar phenomenon was previously observed in the field of interactive image segmentation [30,31].…”

Section: Backpropagating Refinementsupporting

confidence: 86%

“…To achieve this, the idea is to use a backpropagating procedure to refine the result during the inference process. The use of backpropagating refinement in the inference phase has achieved great success for the interactive segmentation task [30,31]. To the best of our knowledge, the use of backpropagating refinement in deep image matting has never been explored before.…”

Section: Backpropagating Refinementmentioning

confidence: 99%

See 1 more Smart Citation

Improving Deep Image Matting via Local Smoothness Assumption

Wang¹,

Xie²,

Han³

et al. 2021

Preprint

View full text Add to dashboard Cite

Natural image matting is a fundamental and challenging computer vision task. Conventionally, the problem is formulated as an underconstrained problem. Since the problem is ill-posed, further assumptions on the data distribution are required to make the problem well-posed. For classical matting methods, a commonly adopted assumption is the local smoothness assumption on foreground and background colors. However, the use of such assumptions was not systematically considered for deep learning based matting methods. In this work, we consider two local smoothness assumptions which can help improving deep image matting models. Based on the local smoothness assumptions, we propose three techniques, i.e., training set refinement, color augmentation and backpropagating refinement, which can improve the performance of the deep image matting model significantly. We conduct experiments to examine the effectiveness of the proposed algorithm. The experimental results show that the proposed method has favorable performance compared with existing matting methods.

show abstract

Section: Backpropagating Refinementsupporting

confidence: 86%

Section: Backpropagating Refinementmentioning

confidence: 99%

Improving Deep Image Matting via Local Smoothness Assumption

Wang¹,

Xie²,

Han³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…The initial annotation proposal can be further refined with additional user input in form of scribble lines. More recently, interactive segmentation using deep learning techniques outperformed previous approaches, such as Deep Extreme Cut [13], f-BRS [14] and Inside Out Guidance [15].…”

Section: B Semi-automatic Annotationmentioning

confidence: 99%

Few-leaf Learning: Weed Segmentation in Grasslands

Güldenring

Boukas

Ravn

et al. 2021

2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Autonomous robotic weeding in grasslands requires robust weed segmentation. Deep learning models can provide solutions to this problem, but they need to be trained on large amounts of images, which in the case of grasslands are notoriously difficult to obtain and manually annotate. In this work we introduce Few-leaf Learning, a concept that facilitates the training of accurate weed segmentation models and can lead to easier generation of weed segmentation datasets with minimal human annotation effort. Our approach builds upon the fact that each plant species within the same field has relatively uniform visual characteristics due to similar environmental influences. Thus, we can train a field-and-day-specific weed segmentation model on synthetic training data stemming from just a handful of annotated weed leaves. We demonstrate the efficacy of our approach for different fields and for two common grassland weeds: Rumex obtusifolius (broad-leaved dock) and Cirsium vulgare (spear thistle). Our code is publicly available at https://github.com/RGring/WeedAnnotator.

show abstract

“…Jang et al [13] proposed a more accurate object segmentation method (BRS) with refining information converted from user interaction by using the backpropagation method. Sofiiuk et al [2] proposed a faster segmentation method (f-BRS) than BRS by performing backpropagation in only part of the model. Zhang et al [3] proposed a method (IOG) for segmenting the target objects through interaction that combines the advantages of the bounding box and click methods.…”

Section: Interactive Object Segmentationmentioning

confidence: 99%

Interactive Part Segmentation Using Edge Images

Park

2021

Applied Sciences

View full text Add to dashboard Cite

As more and more fields utilize deep learning, there is an increasing demand to make suitable training data for each field. The existing interactive object segmentation models can easily make the mask label data because these can accurately segment the area of the target object through user interaction. However, it is difficult to accurately segment the target part in the object using the existing models. We propose a method to increase the accuracy of part segmentation by using the proposed interactive object segmentation model trained only with edge images instead of color images. The results evaluated with the PASCAL VOC Part dataset show that the proposed method can accurately segment the target part compared to the existing interactive object segmentation model and the semantic part-segmentation model.

show abstract

F-BRS: Rethinking Backpropagating Refinement for Interactive Segmentation

Cited by 155 publications

References 22 publications

Improving Deep Image Matting via Local Smoothness Assumption

Improving Deep Image Matting via Local Smoothness Assumption

Few-leaf Learning: Weed Segmentation in Grasslands

Interactive Part Segmentation Using Edge Images

Contact Info

Product

Resources

About