Learning to Refine Object Segments

@inproceedings{Pinheiro2016LearningTR,
  title={Learning to Refine Object Segments},
  author={Pedro H. O. Pinheiro and Tsung-Yi Lin and Ronan Collobert and Piotr Doll{\'a}r},
  booktitle={ECCV},
  year={2016}
}
Object segmentation requires both object-level information and low-level pixel data. [...] Key Method Similarly to skip connections, our approach leverages features at all layers of the net. Unlike skip connections, our approach does not attempt to output independent predictions at each layer. Instead, we first output a coarse ‘mask encoding’ in a feedforward pass, then refine this mask encoding in a top-down pass utilizing features at successively lower layers. The approach is simple, fast, and effective…Expand
Learning to Refine Object Contours with a Top-Down Fully Convolutional Encoder-Decoder Network
TLDR
A novel deep contour detection algorithm with a top-down fully convolutional encoder-decoder network that achieved the state-of-the-art on the BSDS500 dataset, the PASCAL VOC2012 dataset, and the NYU Depth dataset. Expand
DUALMASK - Object Instance Segmentation
In past few years, Convolution Neural Networks have gained a significant attention from vision community due to its state of the art performance in Object Classification task. But when it comes toExpand
Convolutional Networks with Bracket-Style Decoder for Semantic Scene Segmentation
TLDR
A deep convolutional network with bracket-style decoder, namely B-Net, is proposed to leverage the utilization of features learned at middle layers in the backbone networks (encoder) for constructing a final prediction map of densely enhanced semantic information. Expand
Learning Spatial Transforms for Refining Object Segment Proposals
TLDR
This work proposes an efficient deep network that learns 2D spatial transforms to warp an initial object mask towards nearby object region and designs a novel feature pooling strategy in this deep network to predict an affine transformation for each object mask. Expand
Embedding Attention and Residual Network for Accurate Salient Object Detection
TLDR
An efficient fully convolutional salient object detection network is presented and attention weight is employed in a top-down manner which can bridge high level semantic information to help shallow layers better locate salient objects and also filter out noisy response in the background region. Expand
Convolutional Oriented Boundaries: From Image Segmentation to High-Level Tasks
TLDR
Convolutional Oriented Boundaries gives a significant leap in performance over the state-of-the-art, and generalizes very well to unseen categories and datasets, and learning to estimate not only contour strength but also orientation provides more accurate results. Expand
Beyond Skip Connections: Top-Down Modulation for Object Detection
TLDR
Inspired by the human visual pathway, this paper proposes top-down modulations as a way to incorporate fine details into the detection framework, and supplements the standard bottom-up, feedforward ConvNet with a top- down modulation (TDM) network, connected using lateral connections. Expand
Focal Boundary Guided Salient Object Detection
TLDR
This work proposes a novel deep model—Focal Boundary Guided (Focal-BG) network, designed to jointly learn to segment salient object masks and detect salient object boundaries and demonstrates that the joint modeling of salient object boundary and mask helps to better capture the shape details, especially in the vicinity of object boundaries. Expand
Dense image labeling using deep learning
TLDR
End-toend encoder-decoder networks that initially make a coarse-grained prediction which is progressively refined to recover spatial details are proposed, that control information passed forward in order to resolve ambiguity. Expand
A Generative Appearance Model for End-To-End Video Object Segmentation
TLDR
This work proposes a network architecture that learns a powerful representation of the target and background appearance in a single forward pass, and outperforms all published approaches on the large-scale YouTube-VOS dataset. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 51 REFERENCES
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
TLDR
This paper proposes a simple and scalable detection algorithm that improves mean average precision (mAP) by more than 30% relative to the previous best result on VOC 2012 -- achieving a mAP of 53.3%. Expand
Recurrent Convolutional Neural Networks for Scene Labeling
TLDR
This work proposes an approach that consists of a recurrent convolutional neural network which allows us to consider a large input context while limiting the capacity of the model, and yields state-of-the-art performance on both the Stanford Background Dataset and the SIFT FlowDataset while remaining very fast at test time. Expand
Fully Convolutional Networks for Semantic Segmentation
TLDR
It is shown that convolutional networks by themselves, trained end- to-end, pixels-to-pixels, improve on the previous best result in semantic segmentation. Expand
Learning to Segment Object Candidates
TLDR
A new way to generate object proposals is proposed, introducing an approach based on a discriminative convolutional network that obtains substantially higher object recall using fewer proposals and is able to generalize to unseen categories it has not seen during training. Expand
Simultaneous Detection and Segmentation
TLDR
This work builds on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN), introducing a novel architecture tailored for SDS, and uses category-specific, top-down figure-ground predictions to refine the bottom-up proposals. Expand
Learning Hierarchical Features for Scene Labeling
TLDR
A method that uses a multiscale convolutional network trained from raw pixels to extract dense feature vectors that encode regions of multiple sizes centered on each pixel, alleviates the need for engineered features, and produces a powerful representation that captures texture, shape, and contextual information. Expand
Semantic Image Segmentation with Deep Convolutional Nets and Fully Connected CRFs
TLDR
This work brings together methods from DCNNs and probabilistic graphical models for addressing the task of pixel-level classification by combining the responses at the final DCNN layer with a fully connected Conditional Random Field (CRF). Expand
Hypercolumns for object segmentation and fine-grained localization
TLDR
Using hypercolumns as pixel descriptors, this work defines the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel, and shows results on three fine-grained localization tasks: simultaneous detection and segmentation, and keypoint localization. Expand
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
TLDR
This work introduces a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals and further merge RPN and Fast R-CNN into a single network by sharing their convolutionAL features. Expand
Scalable, High-Quality Object Detection
TLDR
It is demonstrated that learning-based proposal methods can effectively match the performance of hand-engineered methods while allowing for very efficient runtime-quality trade-offs. Expand
...
1
2
3
4
5
...