Learning to Refine Object Segments

Pinheiro, Pedro O.; Lin, Tsung-Yi; Collobert, Ronan; Dollár, Piotr

doi:10.48550/arxiv.1603.08695

Cited by 11 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…MCNs [7] category predicted pixels via the result of object detection. In DeepMask [16] and SharpMask [17] two branches for segmentation and object score are engaged. Different form DeepMask, InstanceFCN [18] exploits local coherence rather than high-dimensional features to confirm instances.…”

Section: A Instance Segmentationmentioning

confidence: 99%

Gland Instance Segmentation by Deep Multichannel Neural Networks

Xu¹,

Li²,

Liu³

et al. 2016

Preprint

View full text Add to dashboard Cite

In this paper, we propose a new image instance segmentation method that segments individual glands (instances) in colon histology images. This is a task called instance segmentation that has recently become increasingly important. The problem is challenging since not only do the glands need to be segmented from the complex background, they are also required to be individually identified. Here we leverage the idea of image-to-image prediction in recent deep learning by building a framework that automatically exploits and fuses complex multichannel information, regional, location and boundary patterns in gland histology images. Our proposed system, deep multichannel framework, alleviates heavy feature design due to the use of convolutional neural networks and is able to meet multifarious requirement by altering channels. Compared to methods reported in the 2015 MICCAI Gland Segmentation Challenge and other currently prevalent methods of instance segmentation, we observe state-of-the-art results based on a number of evaluation metrics.

show abstract

Section: A Instance Segmentationmentioning

confidence: 99%

Gland Instance Segmentation by Deep Multichannel Neural Networks

Xu¹,

Li²,

Liu³

et al. 2016

Preprint

View full text Add to dashboard Cite

show abstract

“…Each extra layer has 3 × 3 kernels and 64 channels which play a role in dimension reduction. Inspired by [40], we integrate a "refinement module" R to invert the effect of each pooling layer and double the resolution of its input feature map if necessary. As shown in Figure 3, the refinement stream consists of five stacked refinement modules, each of which corresponds to one pooling layer in the backbone network.…”

Section: Refined Vgg Networkmentioning

confidence: 99%

Instance-Level Salient Object Segmentation

Xie

et al. 2017

2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

222

107

View full text Add to dashboard Cite

Image saliency detection has recently witnessed rapid progress due to deep convolutional neural networks. However, none of the existing methods is able to identify object instances in the detected salient regions. In this paper, we present a salient instance segmentation method that produces a saliency mask with distinct object instance labels for an input image. Our method consists of three steps, estimating saliency map, detecting salient object contours and identifying salient object instances. For the first two steps, we propose a multiscale saliency refinement network, which generates high-quality salient region masks and salient object contours. Once integrated with multiscale combinatorial grouping and a MAP-based subset optimization framework, our method can generate very promising salient object instance segmentation results. To promote further research and evaluation of salient instance segmentation, we also construct a new database of 1000 images and their pixelwise salient instance annotations. Experimental results demonstrate that our proposed method is capable of achieving state-of-the-art performance on all public benchmarks for salient region detection as well as on our new dataset for salient instance segmentation.

show abstract

“…In this paper, we develop a pixel-wise and end-to-end contour detection system, Top-Down Convolutional Encoder-Decoder Network (TD-CEDN), which is inspired by the success of Fully Convolutional Networks (FCN) [23], HED, Encoder-Decoder networks [24], [25], [13] and the bottomup/top-down architecture [26]. Being fully convolutional, the developed TD-CEDN can operate on an arbitrary image size and the encoder-decoder network emphasizes its symmetric structure which is similar to the SegNet [25] and DeconvNet [24] but not the same, as shown in Fig.…”

Section: Raw Imagementioning

confidence: 99%

“…SegNet [25] used the max pooling indices to upsample (without learning) the feature maps and convolved with a trainable decoder network. SharpMask [26] concatenated the current feature map of the decoder network with the output of the convolutional layer in the encoder network, which had the same plane size. Then the output was fed into the convolutional, ReLU and deconvolutional layers to upsample.…”

Section: B Refined Modulementioning

confidence: 99%

“…Fig. 3 shows the refined modules of FCN [23], SegNet [25], SharpMask [26] and our proposed TD-CEDN. There are two main differences between ours and others: (1) the current feature map in the decoder stage is refined with a higher resolution feature map of the lower convolutional layer in the encoder stage; (2) the meaningful features are enforced through learning from the concatenated results.…”

Section: B Refined Modulementioning

confidence: 99%

See 1 more Smart Citation

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

Liu,

Yao,

et al. 2017

Preprint

View full text Add to dashboard Cite

We develop a novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network. Our proposed method, named TD-CEDN, solves two important issues in this low-level vision problem: (1) learning multi-scale and multi-level features; and (2) applying an effective top-down refined approach in the networks. TD-CEDN performs the pixel-wise prediction by means of leveraging features at all layers of the net. Unlike skip connections and previous encoder-decoder methods, we first learn a coarse feature map after the encoder stage in a feedforward pass, and then refine this feature map in a top-down strategy during the decoder stage utilizing features at successively lower layers. Therefore, the deconvolutional process is conducted stepwise, which is guided by Deeply-Supervision Net providing the integrated direct supervision. The above proposed technologies lead to a more precise and clearer prediction. Our proposed algorithm achieved the state-of-the-art on the BSDS500 dataset (ODS F-score of 0.788), the PASCAL VOC2012 dataset (ODS F-score of 0.588), and and the NYU Depth dataset (ODS F-score of 0.735).

show abstract

Learning to Refine Object Segments

Cited by 11 publications

References 0 publications

Gland Instance Segmentation by Deep Multichannel Neural Networks

Gland Instance Segmentation by Deep Multichannel Neural Networks

Instance-Level Salient Object Segmentation

Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network

Contact Info

Product

Resources

About