Weakly-Supervised Semantic Segmentation Network with Deep Seeded Region Growing

Huang, Zilong; Wang, Xinggang; Wang, Jiasi; Liu, Wenyu; Wang, Jingdong

doi:10.1109/cvpr.2018.00733

Cited by 560 publications

(505 citation statements)

References 21 publications

Supporting

Mentioning

476

Contrasting

Unclassified

Order By: Relevance

“…Recent methods (Kolesnikov and Lampert [2016]; Wei et al [2017a]; Wang et al [2018b]; Ahn and Kwak [2018]; Huang et al [2018]; Wei et al [2018]) tackle weakly-supervised semantic segmentation by a twostage procedure, which first generates initial object labels with class activation maps (Zhou et al [2016]), and then trains segmentation networks based on the response maps. Kolesnikov and Lampert [2016] present an end-to-end framework with three modules (seed, expand and constrain) as loss functions, and the class activation maps are used as supervisory signals.…”

Section: Weakly-supervised Semantic Segmentationmentioning

confidence: 99%

“…Ahn and Kwak [2018] learn the pixel affinity from the activation maps and then apply the random walk method to refine them. Huang et al [2018] design a deep seeded region growing algorithm which improves the seed regions to supervise the network.…”

Section: Weakly-supervised Semantic Segmentationmentioning

confidence: 99%

“…The PASCAL VOC 2012 dataset contains 20 object classes and 1 background class with 1464 training images, 1449 validation images, and 1456 testing images. Same as the recent work (Wei et al [2017a]; Ahn and Kwak [2018]; Huang et al [2018]; Wei et al [2018]; Wang et al [2018b]), we use the augmented set with 10582 images from (Hariharan et al [2011]) for training. For the COCO dataset, it contains more complex scenes and more classes (80 classes plus 1 background class) with 80k images for training and 40k images for validation.…”

Section: Settingsmentioning

confidence: 99%

“…The CAM Network is trained with the PyTorch framework and other models are trained with the Caffe package (Jia et al [2014]). Similar to recent weaklysupervised learning methods (Pathak et al [2015]; Kolesnikov and Lampert [2016]; Ahn and Kwak [2018]; Huang et al [2018]), all networks are initialized with the weights of a pre-trained model based on the ImageNet. All the source code and trained models will be made available online.…”

Section: Training Processmentioning

confidence: 99%

“…However, fully-supervised methods require a large amount of pixel-wise annotations, which is time-consuming and expensive. To make semantic segmentation more practical, a number of weakly-supervised methods have been proposed in recent years based on partial information of each image, such as bounding boxes (Dai et al [2015]; Khoreva et al [2017]), scribbles (Lin et al [2016]), points (Bearman et al [2016]), and even class labels (Pathak et al [2015]; Wang et al [2018b]; Ahn and Kwak [2018]; Huang et al [2018]; Wei et al [2018]). In this paper, we present a weakly-supervised semantic segmentation algorithm based only on class labels of an image.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning

Wang

Liu

et al. 2020

Int J Comput Vis

View full text Add to dashboard Cite

Weakly-supervised semantic segmentation is a challenging task as no pixel-wise label information is provided for training. Recent methods have exploited classification networks to localize objects by selecting regions with strong response. While such response map provides sparse information, however, there exist strong pairwise relations between pixels in natural images, which can be utilized to propagate the sparse map to a much denser one. In this paper, we propose an iterative algorithm to learn such pairwise relations, which consists of two branches, a unary segmentation network which learns the label probabilities for each pixel, and a pairwise affinity network which learns affinity matrix and refines the probability map generated from the unary network. The refined results by the pairwise network are then used as supervision to train the unary network, and the procedures are conducted iteratively to obtain better segmentation progressively. To learn reliable pixel affinity without accurate annotation, we also propose to mine confident regions. We show that iteratively training this framework is equivalent to optimizing an energy function with convergence to a local minimum. Experimental results on the PAS-CAL VOC 2012 and COCO datasets demonstrate that the proposed algorithm performs favorably against the state-of-the-art methods.

show abstract

Section: Weakly-supervised Semantic Segmentationmentioning

confidence: 99%

Section: Weakly-supervised Semantic Segmentationmentioning

confidence: 99%

Section: Settingsmentioning

confidence: 99%

Section: Training Processmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning

Wang

Liu

et al. 2020

Int J Comput Vis

View full text Add to dashboard Cite

show abstract

Segmentation of plant residues on soil X‐ray CT images using neural network

Valdes‐Korovkin,

Fomin,

Yudina

2023

Agronomy Journal

View full text Add to dashboard Cite

In soil, plant residues have low contrast making them difficult to detect using X‐ray computed tomography (CT). In this work, we tested a convolutional neural network (U‐Net) for its ability to improve the identification of crop residues in soil samples assembled from aggregates of different size fractions (small, large, water‐stable aggregates, and average aggregate composition). Soil CT images were obtained using a 244 μm resolution. About 2500 soil images were annotated to train the neural network, of which only 631 images were selected for the training data set. Intersection over Union (IoU) was used as a measure of success of segmentation by neural network, which takes values from 0 to 1. In the validation data set, IoU of background was 0.93, IoU of solid phase was 0.95, IoU of pore space was 0.77, and IoU of plant residues was 0.40. However, IoU of plant residues in the total data set increased to 0.7. Soil structure influences the quality of multiphase segmentation of soil CT images. The poorest segmentation of plant residues was in the soil samples composed of average aggregate size composition. The quality of pore space segmentation increased with increasing porosity of the soil sample . The model tends to generalize the large areas occupied by plant residues and overlooks the smaller ones. The low values of the IoU metric for plant residues in the training data set can also be related to insufficient quality of annotation of the original images.This article is protected by copyright. All rights reserved

show abstract