Simultaneous Detection and Segmentation

@inproceedings{Hariharan2014SimultaneousDA,
  title={Simultaneous Detection and Segmentation},
  author={Bharath Hariharan and Pablo Andr{\'e}s Arbel{\'a}ez and Ross B. Girshick and Jitendra Malik},
  booktitle={ECCV},
  year={2014}
}
We aim to detect all instances of a category in an image and, for each instance, mark the pixels that belong to it. We call this task Simultaneous Detection and Segmentation (SDS). Unlike classical bounding box detection, SDS requires a segmentation and not just a box. Unlike classical semantic segmentation, we require individual object instances. We build on recent work that uses convolutional neural networks to classify category-independent region proposals (R-CNN [16]), introducing a novel… CONTINUE READING

Figures, Tables, Results, and Topics from this paper.

Key Quantitative Results

  • We show a 7 point boost (16% relative) over our baselines on SDS, a 5 point boost (10% relative) over state-of-the-art on semantic segmentation, and state-of-the-art performance in object detection.

Citations

Publications citing this paper.
SHOWING 1-10 OF 489 CITATIONS, ESTIMATED 35% COVERAGE

Pixel Offset Regression (POR) for Single-shot Instance Segmentation

  • 2018 15th IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)
  • 2018
VIEW 5 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2017
VIEW 26 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Proposal-Free Network for Instance-Level Object Segmentation

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2017
VIEW 9 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Cross Modal Distillation for Supervision Transfer

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 5 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

Object detection in 20 questions

  • 2016 IEEE Winter Conference on Applications of Computer Vision (WACV)
  • 2016
VIEW 14 EXCERPTS
CITES METHODS & RESULTS
HIGHLY INFLUENCED

Reversible Recursive Instance-Level Object Segmentation

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 14 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Convolutional feature masking for joint object and stuff segmentation

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 20 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Hypercolumns for object segmentation and fine-grained localization

  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
VIEW 18 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2014
2019

CITATION STATISTICS

  • 68 Highly Influenced Citations

  • Averaged 121 Citations per year over the last 3 years

  • 4% Increase in citations per year in 2018 over 2017

References

Publications referenced by this paper.
SHOWING 1-10 OF 32 REFERENCES

Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 19 EXCERPTS
HIGHLY INFLUENTIAL

Bottom-Up Segmentation for Top-Down Detection

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

Multiscale Combinatorial Grouping

  • 2014 IEEE Conference on Computer Vision and Pattern Recognition
  • 2014
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Caffe: An open source convolutional architecture for fast feature embedding

Y. Jia
  • 2013
VIEW 1 EXCERPT

Similar Papers

Loading similar papers…