Hypercolumns for object segmentation and fine-grained localization

  title={Hypercolumns for object segmentation and fine-grained localization},
  author={Bharath Hariharan and Pablo Andr{\'e}s Arbel{\'a}ez and Ross B. Girshick and Jitendra Malik},
  journal={2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as a feature representation. However, the information in this layer may be too coarse spatially to allow precise localization. On the contrary, earlier layers may be precise in localization but will not capture semantics. To get the best of both worlds, we define the hypercolumn at a pixel as the vector of activations of all CNN units above that pixel. Using hypercolumns as pixel descriptors… CONTINUE READING
Highly Influential
This paper has highly influenced 75 other papers. REVIEW HIGHLY INFLUENTIAL CITATIONS
Highly Cited
This paper has 818 citations. REVIEW CITATIONS
Recent Discussions
This paper has been referenced on Twitter 6 times over the past 90 days. VIEW TWEETS

From This Paper

Topics from this paper.
531 Citations
47 References
Similar Papers


Publications citing this paper.
Showing 1-10 of 531 extracted citations

818 Citations

Citations per Year
Semantic Scholar estimates that this publication has 818 citations based on the available data.

See our FAQ for additional information.


Publications referenced by this paper.
Showing 1-10 of 47 references

Similar Papers

Loading similar papers…