A Reliability Object Layer for Deep Hashing-Based Visual Indexing
| Autor: | Konstantinos Gkountakos, Georgios Th. Papadopoulos, Petros Daras, Theodoros Semertzidis |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Artificial neural network
Computer science business.industry Deep learning Search engine indexing Hash function Pattern recognition Context (language use) 02 engineering and technology Image segmentation 010501 environmental sciences Object (computer science) 01 natural sciences 0202 electrical engineering electronic engineering information engineering Object type 020201 artificial intelligence & image processing Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | MultiMedia Modeling ISBN: 9783030057152 MMM (2) |
| DOI: | 10.1007/978-3-030-05716-9_11 |
| Popis: | Nowadays, time-efficient search and retrieval of visually similar content has emerged as a great necessity, while at the same time it constitutes an outstanding research challenge. The latter is further reinforced by the fact that millions of images and videos are generated on a daily basis. In this context, deep hashing techniques, which aim at estimating a very low dimensional binary vector for characterizing each image, have been introduced for realizing realistically fast visual-based search tasks. In this paper, a novel approach to deep hashing is proposed, which explicitly takes into account information about the object types that are present in the image. For achieving this, a novel layer has been introduced on top of current Neural Network (NN) architectures that aims to generate a reliability mask, based on image semantic segmentation information. Thorough experimental evaluation, using four datasets, proves that incorporating local-level information during the hash code learning phase significantly improves the similar retrieval results, compared to state-of-art approaches. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|