Feedforward semantic segmentation with zoom-out features

Mostajabi, Mohammadreza; Yadollahpour, Payman; Shakhnarovich, Gregory

doi:10.48550/arxiv.1412.0774

Cited by 10 publications

(21 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Method test IOU MSRA-CFM [8] 61.8 FCN-8s [25] 62.2 Hypercolumn [17] 62.6 TTI-Zoomout-16 [28] 64.4 DeepLab-CRF-LargeFOV [5] 70.3 BoxSup (Semi, with weak COCO) [9] 71.0 DeepLab-CRF-LargeFOV (Multi-scale net) [5] 71.6 Oxford TVG CRF RNN VOC [42] 72.0 Oxford TVG CRF RNN COCO [42] 74.…”

Section: Test Resultsmentioning

confidence: 99%

“…Semantic image segmentation refers to the problem of assigning a semantic label (such as "person", "car" or "dog") to every pixel in the image. Various approaches have been tried over the years, but according to the results on the challenging Pascal VOC 2012 segmentation benchmark, the best performing methods all use some kind of Deep Convolutional Neural Network (DCNN) [2,5,8,14,25,28,42].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Papandreou

Chen

Murphy

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

1,042

1,025

View full text Add to dashboard Cite

Deep convolutional neural networks (DCNNs) trained on a large number of images with strong pixel-level annotations have recently significantly pushed the state-of-art in semantic image segmentation. We study the more challenging problem of learning DCNNs for semantic image segmentation from either (1) weakly annotated training data such as bounding boxes or image-level labels or (2) a combination of few strongly labeled and many weakly labeled images, sourced from one or multiple datasets. We develop Expectation-Maximization (EM) methods for semantic image segmentation model training under these weakly supervised and semi-supervised settings. Extensive experimental evaluation shows that the proposed techniques can learn models delivering competitive results on the challenging PASCAL VOC 2012 image segmentation benchmark, while requiring significantly less annotation effort. We share source code implementing the proposed system at https: //bitbucket.org/deeplab/deeplab-public.

show abstract

Section: Test Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Papandreou

Chen

Murphy

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

1,042

1,025

View full text Add to dashboard Cite

show abstract

“…There are several semantic segmentation methods based on classification. Mostajabi et al [18] and Farabet et al [6] classify multi-scale superpixels into predefined categories and combine the classification results for pixel-wise labeling. Some algorithms [3,9,10] classify region proposals and refine the labels in the image-level segmentation map to obtain the final segmentation.…”

Section: Related Workmentioning

confidence: 99%

“…Convolutional neural networks (CNN) have shown excellent performance in various visual recognition problems such as image classification [15,22,23], object detection [7,9], semantic segmentation [6,18], and action recognition [12,21]. The representation power of CNNs leads to successful results; a combination of feature descriptors extracted from CNNs and simple off-the-shelf classifiers works very well in practice.…”

Section: Introductionmentioning

confidence: 99%

Learning Deconvolution Network for Semantic Segmentation

Noh

Hong

Han

2015

2015 IEEE International Conference on Computer Vision (ICCV)

3,727

2,401

View full text Add to dashboard Cite

We propose a novel semantic segmentation algorithm by learning a deconvolution network. We learn the network on top of the convolutional layers adopted from VGG 16-layer net. The deconvolution network is composed of deconvolution and unpooling layers, which identify pixel-wise class labels and predict segmentation masks. We apply the trained network to each proposal in an input image, and construct the final semantic segmentation map by combining the results from all proposals in a simple manner. The proposed algorithm mitigates the limitations of the existing methods based on fully convolutional networks by integrating deep deconvolution network and proposal-wise prediction; our segmentation method typically identifies detailed structures and handles objects in multiple scales naturally. Our network demonstrates outstanding performance in PASCAL VOC 2012 dataset, and we achieve the best accuracy (72.5%) among the methods trained with no external data through ensemble with the fully convolutional network.

show abstract

“…In the past few months, tremendous progress has been made in the field of semantic segmentation [12,22,13,6,5,23]. Deep convolutional neural networks (CNNs) [19,18] that play as rich hierarchical feature extractors are a key to these methods.…”

Section: Introductionmentioning

confidence: 99%

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Dai

Sun

2015

2015 IEEE International Conference on Computer Vision (ICCV)

983

747

View full text Add to dashboard Cite

Recent leading approaches to semantic segmentation rely on deep convolutional networks trained with humanannotated, pixel-level segmentation masks. Such pixelaccurate supervision demands expensive labeling effort and limits the performance of deep networks that usually benefit from more training data. In this paper, we propose a method that achieves competitive accuracy but only requires easily obtained bounding box annotations. The basic idea is to iterate between automatically generating region proposals and training convolutional networks. These two steps gradually recover segmentation masks for improving the networks, and vise versa. Our method, called "BoxSup", produces competitive results (e.g., 62.0% mAP for validation) supervised by boxes only, on par with strong baselines (e.g., 63.8% mAP) fully supervised by masks under the same setting. By leveraging a large amount of bounding boxes, BoxSup further unleashes the power of deep convolutional networks and yields state-of-the-art results on PAS-CAL VOC 2012 and PASCAL-CONTEXT [24].

show abstract

Feedforward semantic segmentation with zoom-out features

Cited by 10 publications

References 0 publications

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Weakly-and Semi-Supervised Learning of a Deep Convolutional Network for Semantic Image Segmentation

Learning Deconvolution Network for Semantic Segmentation

BoxSup: Exploiting Bounding Boxes to Supervise Convolutional Networks for Semantic Segmentation

Contact Info

Product

Resources

About