Learning Short-Cut Connections for Object Counting

By Daniel Oñoro-Rubio, Mathias Niepert, Roberto Javier López-Sastre. 2018

11 citations recorded by the source corpus.

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.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

NAS-FPN: Learning Scalable Feature Pyramid Architecture for Object Detection (2019, background): “ Despite it is an active research area, most architecture designs of cross-scale connections remain shallow compared to the backbone model. In addition to manually design the cross-scale connections, [5,27] propose to learn the connections through gating mechanism for visual counting and dense label”
JHU-CROWD++: Large-Scale Crowd Counting Dataset and A Benchmark Method (2020, methodology): “Recent advances in CNNs have been exploited for the task of crowd counting and these methods [4, 5, 6, 7, 7, 22, 23, 52, 53, 54, 55, 56] have demonstrated significant improvements over the traditional methods.”
Learning Spatial Fusion for Single-Shot Object Detection (2019, background): “[28] proposes a sigmoid gating unit in the skip connection between convolutional and deconvolutional layers of features at each single level for visual counting.”