Hypercolumns for object segmentation and fine-grained localization

@article{Hariharan2015HypercolumnsFO,
  title={Hypercolumns for object segmentation and fine-grained localization},
  author={Bharath Hariharan and Pablo Arbel{\'a}ez and Ross B. Girshick and Jitendra Malik},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2015},
  pages={447-456}
}
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a feature representation. [...] Key Result Using hypercolumns as pixel descriptors, we show results on three fine-grained localization tasks: simultaneous detection and segmentation [22], where we improve state-of-the-art from 49.7 mean APr [22] to 60.0, keypoint localization, where we get a 3.3 point boost over [20], and part labeling, where we show a 6.6 point gain over a strong baseline.Expand
1,217 Citations
Object Instance Segmentation and Fine-Grained Localization Using Hypercolumns
  • 48
  • PDF
Laplacian Pyramid Reconstruction and Refinement for Semantic Segmentation
  • 294
  • PDF
Memory-Efficient Deep Salient Object Segmentation Networks on Gridized Superpixels
  • 2
  • PDF
Learning to Compose Hypercolumns for Visual Correspondence
  • 7
  • PDF
Region-Based Convolutional Networks for Accurate Object Detection and Segmentation
  • 1,255
  • PDF
Rethinking Atrous Convolution for Semantic Image Segmentation
  • 2,392
  • PDF
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation
  • 86
  • Highly Influenced
  • PDF
Learning to segment with image-level annotations
  • 75
  • PDF
Fully Convolutional Networks for Semantic Segmentation
  • 9,994
  • PDF
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 45 REFERENCES
Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
  • 13,523
  • PDF
Simultaneous Detection and Segmentation
  • 922
  • PDF
Fully Convolutional Networks for Semantic Segmentation
  • 9,994
  • PDF
Convolutional feature masking for joint object and stuff segmentation
  • Jifeng Dai, Kaiming He, Jian Sun
  • Computer Science
  • 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2015
  • 342
  • Highly Influential
  • PDF
Very Deep Convolutional Networks for Large-Scale Image Recognition
  • 47,726
  • Highly Influential
  • PDF
Learning Hierarchical Features for Scene Labeling
  • 2,206
  • PDF
Part-Based R-CNNs for Fine-Grained Category Detection
  • 771
  • PDF
Learning to localize detected objects
  • Qieyun Dai, Derek Hoiem
  • Computer Science
  • 2012 IEEE Conference on Computer Vision and Pattern Recognition
  • 2012
  • 47
  • PDF
Bottom-Up Segmentation for Top-Down Detection
  • 131
  • PDF
...
1
2
3
4
5
...