Proposal-Free Network for Instance-Level Object Segmentation

Lin, Liang; Wei, Yunchao; Shen, Xiaohui; Yang, Jianchao; Yan, Shuicheng

doi:10.1109/tpami.2017.2775623

Cited by 180 publications

(155 citation statements)

References 56 publications

Supporting

Mentioning

153

Contrasting

Order By: Relevance

“…Current state-of-the-art solutions to this challenging problem can be classified into the proposal-based and proposal-free approaches [34,28,40]. The proposal-based approaches regard it as an extension to the classic object detection task [46,39,44,15].…”

Section: Introductionmentioning

confidence: 99%

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Gao

Shan

Wang

et al. 2019

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

243

146

View full text Add to dashboard Cite

Recently, proposal-free instance segmentation has received increasing attention due to its concise and efficient pipeline. Generally, proposal-free methods generate instance-agnostic semantic segmentation labels and instance-aware features to group pixels into different object instances. However, previous methods mostly employ separate modules for these two sub-tasks and require multiple passes for inference. We argue that treating these two subtasks separately is suboptimal. In fact, employing multiple separate modules significantly reduces the potential for application. The mutual benefits between the two complementary sub-tasks are also unexplored. To this end, this work proposes a single-shot proposal-free instance segmentation method that requires only one single pass for prediction. Our method is based on a pixel-pair affinity pyramid, which computes the probability that two pixels belong to the same instance in a hierarchical manner. The affinity pyramid can also be jointly learned with the semantic class labeling and achieve mutual benefits. Moreover, incorporating with the learned affinity pyramid, a novel cascaded graph partition module is presented to sequentially generate instances from coarse to fine. Unlike previous time-consuming graph partition methods, this module achieves 5× speedup and 9% relative improvement on Average-Precision (AP). Our approach achieves state-of-the-art results on the challenging Cityscapes dataset.

show abstract

Section: Introductionmentioning

confidence: 99%

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Gao

Shan

Wang

et al. 2019

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

243

146

View full text Add to dashboard Cite

show abstract

“…The best three scores in each row are shown in red, blue, and green, respectively. SOS [20], the DSN excludes the number 0 because dataset1K have no image without a salient object. The matrix presents the percentage of results compared to the ground truth.…”

Section: B Results and Comparisonsmentioning

confidence: 99%

Salient instance segmentation via subitizing and clustering

et al. 2020

View full text Add to dashboard Cite

The goal of salient region detection is to identify the regions of an image that attract the most attention. Many methods have achieved state-of-the-art performance levels on this task. Recently, salient instance segmentation has become an even more challenging task than traditional salient region detection; however, few of the existing methods have concentrated on this underexplored problem. Unlike the existing methods, which usually employ object proposals to roughly count and locate object instances, our method applies salient objects subitizing to predict an accurate number of instances for salient instance segmentation. In this paper, we propose a multitask densely connected neural network (MDNN) to segment salient instances in an image. In contrast to existing approaches, our framework is proposal-free and category-independent. The MDNN contains two parallel branches: the first is a densely connected subitizing network (DSN) used for subitizing prediction; the second is a densely connected fully convolutional network (DFCN) used for salient region detection. The MDNN simultaneously outputs saliency maps and salient object subitizing. Then, an adaptive deep feature-based spectral clustering operation segments the salient regions into instances based on the subitizing and saliency maps. The experimental results on both salient region detection and salient instance segmentation datasets demonstrate the satisfactory performance of our framework. Notably, its AP r @0.7 reaches 60.14% in the salient instance dataset, surpasses the state-of-the-art methods by about 5%.

show abstract

“…Outputs of SpaNet are then post-processed through a simple yet effective clustering algorithm to achieve instance-level segmentation. Our contributions can be summarized as: i) a deep learning based proposal-free framework for nuclei instance segmentation having low computational cost and simple post-processing steps inspired by [9], ii) a spatially-aware network architecture, which is equipped with a novel multi-scale dense convolutional unit, iii) incorporating a nuclei detection map for estimating the number of clusters per nuclei clump, iv) achieving state-of-the-art results on a well-known publicly available multi-organ data set.…”

Section: Introductionmentioning

confidence: 99%

Nuclear Instance Segmentation Using a Proposal-Free Spatially Aware Deep Learning Framework

Koohbanani

Jahanifar²,

Gooya

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Nuclear segmentation in histology images is a challenging task due to significant variations in the shape and appearance of nuclei. One of the main hurdles in nuclear instance segmentation is overlapping nuclei where a smart algorithm is needed to separate each nucleus. In this paper, we introduce a proposal-free deep learning based framework to address these challenges. To this end, we propose a spatially-aware network (SpaNet) to capture spatial information in a multi-scale manner. A dual-head variation of the SpaNet is first utilized to predict the pixel-wise segmentation and centroid detection maps of nuclei. Based on these outputs, a single-head SpaNet predicts the positional information related to each nucleus instance. Spectral clustering method is applied on the output of the last SpaNet, which utilizes the nuclear mask and the Gaussian-like detection map for determining the connected components and associated cluster identifiers, respectively. The output of the clustering method is the final nuclear instance segmentation mask. We applied our method on a publicly available multi-organ data set 5 and achieved state-of-the-art performance for nuclear segmentation.

show abstract

Proposal-Free Network for Instance-Level Object Segmentation

Cited by 180 publications

References 56 publications

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

SSAP: Single-Shot Instance Segmentation With Affinity Pyramid

Salient instance segmentation via subitizing and clustering

Nuclear Instance Segmentation Using a Proposal-Free Spatially Aware Deep Learning Framework

Contact Info

Product

Resources

About