Conference paper Open Access

Learning Short-Cut Connections for Object Counting

Daniel Oñoro-Rubio; Mathias Niepert; Roberto J. López-Sastre


Citation Style Language JSON Export

{
  "publisher": "Zenodo", 
  "DOI": "10.5281/zenodo.3813490", 
  "language": "akh", 
  "title": "Learning Short-Cut Connections for Object Counting", 
  "issued": {
    "date-parts": [
      [
        2018, 
        11, 
        15
      ]
    ]
  }, 
  "abstract": "<p>Object counting is an important task in computer vision due to its growing demand in applications such as traffic monitoring or surveillance. In this paper, we consider object counting as a learning problem of a joint feature extraction and pixel-wise object density estimation with Convolutional-Deconvolutional networks. We introduce a novel counting model, named Gated U-Net (GU-Net). Specifically, we propose to enrich the U-Net architecture with the concept of learnable short-cut connections. Standard short-cut connections are connections between layers in deep neural networks which skip at least one intermediate layer. Instead of simply setting short-cut connections, we propose to learn these connections from data. Therefore, our short-cuts can work as gating units, which optimize the flow of information between convolutional and deconvolutional layers in the U-Net architecture. We evaluate the introduced GU-Net architecture on three commonly used benchmark data sets for object counting. GU-Nets consistently outperform the base U-Net architecture, and achieve state-of-the-art performance.</p>", 
  "author": [
    {
      "family": "Daniel O\u00f1oro-Rubio"
    }, 
    {
      "family": "Mathias Niepert"
    }, 
    {
      "family": "Roberto J. L\u00f3pez-Sastre"
    }
  ], 
  "version": "v.2", 
  "type": "paper-conference", 
  "id": "3813490"
}
13
11
views
downloads
All versions This version
Views 1313
Downloads 1111
Data volume 20.8 MB20.8 MB
Unique views 1212
Unique downloads 1010

Share

Cite as