Hypercolumns for Object Segmentation and Fine-grained Localization
arXiv:1411.5752
Abstract
Recognition algorithms based on convolutional networks (CNNs) typically use the output of the last layer as feature representation. However, the information in this layer may be too coarse 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[22] mean AP^r 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.
CVPR Camera ready
References in corpus (7)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- DeepPose: Human Pose Estimation via Deep Neural Networks
- Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
- Convolutional Feature Masking for Joint Object and Stuff Segmentation
- Simultaneous Detection and Segmentation
- R-CNNs for Pose Estimation and Action Detection
- Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts
Cited by in corpus (8)
- Weakly- and Semi-Supervised Learning of a DCNN for Semantic Image Segmentation
- Evolution of Image Segmentation using Deep Convolutional Neural Network: A Survey
- Good Practice in CNN Feature Transfer
- U-Net: Convolutional Networks for Biomedical Image Segmentation
- Deep Learning for Semantic Part Segmentation with High-Level Guidance
- Learning to count with deep object features
- Contour Detection Using Cost-Sensitive Convolutional Neural Networks
- What's in the box? Explaining the black-box model through an evaluation of its interpretable features