Corpus ID: 11307061

FeaBoost: Joint Feature and Label Refinement for Semantic Segmentation

@inproceedings{Niu2017FeaBoostJF,
  title={FeaBoost: Joint Feature and Label Refinement for Semantic Segmentation},
  author={Yulei Niu and Zhiwu Lu and Songfang Huang and Xin Gao and Ji-Rong Wen},
  booktitle={AAAI},
  year={2017}
}
We propose a novel approach, called FeaBoost, to image semantic segmentation with only image-level labels taken as weakly-supervised constraints. [...] Key Method By taking these two evidences into consideration, semantic segmentation is formulated as joint feature and label refinement over superpixels. Furthermore, we develop an efficient FeaBoost algorithm to solve such optimization problem. Extensive experiments on the MSRC and LabelMe datasets demonstrate the superior performance of our FeaBoost approach in…Expand
Domain-Specific Embedding Network for Zero-Shot Recognition
TLDR
A novel Domain-Specific Embedding Network (DSEN) that can apply specific projections to different domains for unbiased embedding, as well as several domain constraints. Expand
Face Parsing With RoI Tanh-Warping
TLDR
This work proposes a novel RoI Tanh-warping operator that combines the central vision and the peripheral vision together and addresses the dilemma between a limited sized RoI for focusing and an unpredictable area of surrounding context for peripheral information. Expand
Zero-Shot Visual Recognition Using Semantics-Preserving Adversarial Embedding Networks
TLDR
Through adversarial learning of the two subspaces, SP-AEN can transfer the semantics from the reconstructive subspace to the discriminative one, accomplishing the improved zero-shot recognition of unseen classes. Expand
Putting deep learning in perspective for pest management scientists
  • R. Clark
  • Medicine, Computer Science
  • Pest management science
  • 2020
TLDR
This Perspective tries to put deep learning into a broader mechanistic and historical context by showing how it relates to older forms of artificial intelligence; by providing a general explanation of how it operates; and by exploring some of the challenges involved in its implementation. Expand

References

SHOWING 1-10 OF 34 REFERENCES
Sparse Reconstruction for Weakly Supervised Semantic Segmentation
TLDR
A new way of evaluating classification models for semantic segmentation given weekly supervised labels is developed, based on Gaussian Mixture Models, which uses Iterative Merging Update algorithm to obtain the best parameters for the classification models. Expand
Weakly-Supervised Dual Clustering for Image Semantic Segmentation
TLDR
A novel Weakly-Supervised Dual Clustering approach for image semantic segmentation with image-level labels, i.e., collaboratively performing image segmentation and tag alignment with those regions using an iterative CCCP procedure. Expand
Weakly supervised semantic segmentation with a multi-image model
TLDR
A novel method for weakly supervised semantic segmentation using a multi-image model (MIM) - a graphical model for recovering the pixel labels of the training images and introducing an “objectness” potential, that helps separating objects from background classes. Expand
Weakly Supervised RBM for Semantic Segmentation
TLDR
A weakly supervised Restricted Boltzmann Machines (WRBM) approach to deal with the task of semantic segmentation with only image-level labels available, which deals with the problems of label imbalance and diverse backgrounds by adapting the block size to the label frequency and appending hidden response blocks corresponding to backgrounds respectively. Expand
Learning to segment under various forms of weak supervision
TLDR
This work proposes a unified approach that incorporates various forms of weak supervision - image level tags, bounding boxes, and partial labels - to produce a pixel-wise labeling on the challenging Siftflow dataset. Expand
Weakly supervised structured output learning for semantic segmentation
TLDR
A parametric family of structured models is defined, were each model weights visual cues in a different way and a Maximum Expected Agreement model selection principle is proposed that evaluates the quality of a model from the family without looking at superpixel labels. Expand
Towards weakly supervised semantic segmentation by means of multiple instance and multitask learning
  • A. Vezhnevets, J. Buhmann
  • Computer Science
  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
TLDR
An external task of geometric context estimation is used to improve on the task of semantic segmentation, using Semantic Texton Forest (STF) as the basic framework and extending it for the MIL setting. Expand
Associative hierarchical CRFs for object class image segmentation
TLDR
This work proposes a hierarchical random field model, that allows integration of features computed at different levels of the quantisation hierarchy, and evaluates its efficiency on some of the most challenging data-sets for object class segmentation, and shows it obtains state-of-the-art results. Expand
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
Semantic segmentation using regions and parts
TLDR
A novel design for region-based object detectors that integrates efficiently top-down information from scanning-windows part models and global appearance cues is proposed that produces class-specific scores for bottom-up regions, and then aggregate the votes of multiple overlapping candidates through pixel classification. Expand
...
1
2
3
4
...