Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation

By George Papandreou, Liang-Chieh Chen, Kevin P. Murphy, Alan L. Yuille. 2015

413 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Webly Supervised Learning of Convolutional Networks (2015, background): “weak or noisy labels [12, 37, 13, 51, 58]. There are some recent works showcasing that CNNs trained in a weakly supervised setting can also develop detailed information about the object intrinsically [47, 35, 39, 6, 38]. However, different from the assumptions in most weakly-supervised approaches, h”
The Cityscapes Dataset for Semantic Urban Scene Understanding (2016, methodology): “Methods that leverage a CRF for regularization [9, 40, 48, 81] tend to over smooth small objects, c.”
Instance-Aware Semantic Segmentation via Multi-task Network Cascades (2015, background): “Since the development of fully convolutional networks (FCNs) [23], the accuracy of semantic segmentation has been improved rapidly [5, 24, 6, 31] thanks to deeply learned features [20, 27], large-scale annotations [22], and advanced reasoning over graphical models [5, 31].”
DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs (2016, methodology): “DeepLab-CRF-LargeFOV-StrongWeak [58] 64.”
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs (2014, methodology): “Recently, we have pursued model training with weakly supervised annotations, in the form of bounding boxes or image-level labels (Papandreou et al., 2015).”
Conditional Random Fields as Recurrent Neural Networks (2015, methodology): “rning strategies. These are plain FCN-8s without applying CRF, and with CRF as a postprocessing method disconnected from the training of FCN, which is comparable to the approach described in [10] and [41]. The results are reported in Table 1 and show a clear advantage of the end-to-end strategy over”
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation (2018, background): “, image pyramid) [18, 16, 58, 44, 11, 9] or those that adopt probabilistic graphical models (such as DenseCRF [37] with efficient inference algorithm [2]) [8, 4, 82, 44, 48, 55, 63, 34, 72, 6, 7, 9].”
Rethinking Atrous Convolution for Semantic Image Segmentation (2017, background): “2 for illustration) that exploit context information for semantic segmentation [25, 13, 52, 8, 81, 46, 55, 63, 75].”
Learning Deconvolution Network for Semantic Segmentation (2015, methodology): “Note that only the images in PASCAL VOC 2012 augmented datasets are used for training in our experiment, whereas some state-of-theart algorithms [2, 21] also employ Microsoft COCO to improve performance.”
Efficient Piecewise Training of Deep Structured Models for Semantic Segmentation (2015, positive): “DeepLab-CRF [3] performs bilinear upsampling of the prediction score map to the input image size and apply the dense CRF method [24] to refine the object boundary by leveraging the color contrast information.”
SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation (2015, background): “Now there is an active interest for semantic pixel-wise labelling [2], [3], [4],[6], [7], [8], [9], [10], [11], [12], [13], [14], [15].”
Semantic Image Segmentation via Deep Parsing Network (2015, methodology): “With deep models, these works [23, 24, 25, 22, 3, 28, 39, 30, 19] demonstrated encouraging results using simple definition of the pairwise function or even ignore it.”
UberNet: Training a Universal Convolutional Neural Network for Low-, Mid-, and High-Level Vision Using Diverse Datasets and Limited Memory (2016, methodology): “mean IoU Deeplab -COCO + CRF [78] 70.4 Deeplab Multi-Scale [49] 72.1 Deeplab Multi-Scale -CRF [49] 74. tecture.”
Attention to Scale: Scale-Aware Semantic Image Segmentation (2015, neutral): “7 DeepLab-MSc-CRF-COCO-LargeFOV [43] 73.”