Conference paper Open Access

Learning Short-Cut Connections for Object Counting

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

JSON-LD ( Export

  "inLanguage": {
    "alternateName": "akh", 
    "@type": "Language", 
    "name": "Angal Heneng"
  "description": "<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>", 
  "license": "", 
  "creator": [
      "affiliation": "NEC Lab Europe", 
      "@type": "Person", 
      "name": "Daniel O\u00f1oro-Rubio"
      "affiliation": "NEC Lab Europe", 
      "@type": "Person", 
      "name": "Mathias Niepert"
      "affiliation": "University de Alcal\u00e1 de Henares", 
      "@type": "Person", 
      "name": "Roberto J. L\u00f3pez-Sastre"
  "headline": "Learning Short-Cut Connections for Object Counting", 
  "image": "", 
  "datePublished": "2018-11-15", 
  "url": "", 
  "version": "v.2", 
  "@type": "ScholarlyArticle", 
  "@context": "", 
  "identifier": "", 
  "@id": "", 
  "workFeatured": {
    "@type": "Event", 
    "name": "BMBC 2018"
  "name": "Learning Short-Cut Connections for Object Counting"
All versions This version
Views 3434
Downloads 2020
Data volume 37.7 MB37.7 MB
Unique views 3333
Unique downloads 1818


Cite as