Header menu link for other important links
X
Deep neural networks with inexact matching for person re-identification
, Arulkumar Subramaniam, Moitreya Chatterjee
Published in Neural information processing systems foundation
2016
Pages: 2675 - 2683
Abstract
Person Re-Identification is the task of matching images of a person across multiple camera views. Almost all prior approaches address this challenge by attempting to learn the possible transformations that relate the different views of a person from a training corpora. Then, they utilize these transformation patterns for matching a query image to those in a gallery image bank at test time. This necessitates learning good feature representations of the images and having a robust feature matching technique. Deep learning approaches, such as Convolutional Neural Networks (CNN), simultaneously do both and have shown great promise recently. In this work, we propose two CNN-based architectures for Person Re-Identification. In the first, given a pair of images, we extract feature maps from these images via multiple stages of convolution and pooling. A novel inexact matching technique then matches pixels in the first representation with those of the second. Furthermore, we search across a wider region in the second representation for matching. Our novel matching technique allows us to tackle the challenges posed by large viewpoint variations, illumination changes or partial occlusions. Our approach shows a promising performance and requires only about half the parameters as a current state-of-the-art technique. Nonetheless, it also suffers from false matches at times. In order to mitigate this issue, we propose a fused architecture that combines our inexact matching pipeline with a state-of-the-art exact matching technique. We observe substantial gains with the fused model over the current state-of-the-art on multiple challenging datasets of varying sizes, with gains of up to about 21%. © 2016 NIPS Foundation - All Rights Reserved.
About the journal
JournalAdvances in Neural Information Processing Systems
PublisherNeural information processing systems foundation
ISSN10495258
Open AccessNo
Concepts (14)
  •  related image
    Convolution
  •  related image
    Deep learning
  •  related image
    Deep neural networks
  •  related image
    Network architecture
  •  related image
    Neural networks
  •  related image
    CNN-BASED ARCHITECTURE
  •  related image
    Convolutional neural network
  •  related image
    EXACT-MATCHING TECHNIQUES
  •  related image
    Feature representation
  •  related image
    ILLUMINATION CHANGES
  •  related image
    PERSON RE IDENTIFICATIONS
  •  related image
    State-of-the-art techniques
  •  related image
    TRANSFORMATION PATTERNS
  •  related image
    Image processing