Hypercolumns for object segmentation and fine-grained localization
Bharath Hariharan, Pablo Arbeláez, Ross Girshick et al. · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · 2015
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, 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.
Cited by 1,475 works. doi:10.1109/cvpr.2015.7298642
Authors
References
- ImageNet classification with deep convolutional neural networks
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Rich Feature Hierarchies for Accurate Object Detection and Semantic Segmentation
- Receptive fields, binocular interaction and functional architecture in the cat's visual cortex
- Backpropagation Applied to Handwritten Zip Code Recognition
- Fully convolutional networks for semantic segmentation
- Object Detection with Discriminatively Trained Part-Based Models
- The Laplacian Pyramid as a Compact Image Code
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- LIBLINEAR: A Library for Large Linear Classification