publication . Other literature type . Conference object . 2017

Incorporation Of Semantic Segmentation Information In Deep Hashing Techniques For Image Retrieval

Gkountakos Konstantinos; Semertzidis Theodoros; Papadopoulos Georgios Th.; Daras Petros;
Open Access English
  • Published: 29 Jun 2017
  • Publisher: Zenodo
Extracting discriminative image features for similarity search in nowadays large-scale databases becomes an imperative issue of paramount importance. To address the so called task of Approximate Nearest Neighbor (ANN) search in large visual dataset, deep hashing methods (i.e. approaches that make use of the recent deep learning paradigm in computer vision) have recently been introduced. In this paper, a novel approach to deep hashing is proposed, which incorporates local-level information, in the form of image semantic segmentation masks, during the hash code learning step. The proposed framework makes use of pixel-level classification labels, i.e. following a p...
free text keywords: Deep hashing, Binary codes, Segmentation mask, Training, Neural networks, Hashing, Deep learning, Image retrieval, Image segmentation, Nearest neighbor search, Hash function, Feature (computer vision), Machine learning, computer.software_genre, computer, Supervised learning, Feature extraction, Artificial intelligence, business.industry, business, Computer science
Funded by
Detecting and ANalysing TErrorist-related online contents and financing activities
  • Funder: European Commission (EC)
  • Project Code: 700367
  • Funding stream: H2020 | IA
Download fromView all 5 versions
Other literature type . 2017
Provider: Datacite
Conference object . 2018
Provider: ZENODO
Conference object . 2017
Provider: ZENODO
Powered by OpenAIRE Research Graph
Any information missing or wrong?Report an Issue