Browsing by Subject "Benchmark datasets"

Now showing 1 - 4 of 4

Open Access
Attributes2Classname: a discriminative model for attribute-based unsupervised zero-shot learning
(IEEE, 2017-10) Demirel, B.; Cinbiş, Ramazan Gökberk; İkizler-Cinbiş, N.
We propose a novel approach for unsupervised zero-shot learning (ZSL) of classes based on their names. Most existing unsupervised ZSL methods aim to learn a model for directly comparing image features and class names. However, this proves to be a difficult task due to dominance of non-visual semantics in underlying vector-space embeddings of class names. To address this issue, we discriminatively learn a word representation such that the similarities between class and combination of attribute names fall in line with the visual similarity. Contrary to the traditional zero-shot learning approaches that are built upon attribute presence, our approach bypasses the laborious attributeclass relation annotations for unseen classes. In addition, our proposed approach renders text-only training possible, hence, the training can be augmented without the need to collect additional image data. The experimental results show that our method yields state-of-the-art results for unsupervised ZSL in three benchmark datasets. © 2017 IEEE.
Open Access
Conceptfusion: A flexible scene classification framework
(Springer, 2015-03-04) Saraç, Mustafa İlker; işcen, Ahmet; Gölge, Eren; Duygulu, Pınar
We introduce ConceptFusion, a method that aims high accuracy in categorizing large number of scenes, while keeping the model relatively simpler and efficient for scalability. The proposed method combines the advantages of both low-level representations and high-level semantic categories, and eliminates the distinctions between different levels through the definition of concepts. The proposed framework encodes the perspectives brought through different concepts by considering them in concept groups that are ensembled for the final decision. Experiments carried out on benchmark datasets show the effectiveness of incorporating concepts in different levels with different perspectives. © Springer International Publishing Switzerland 2015.
Open Access
FAME: Face association through model evolution
(IEEE, 2015-06) Gölge, Eren; Duygulu, Pınar
We attack the problem of building classifiers for public faces from web images collected through querying a name. The search results are very noisy even after face detection, with several irrelevant faces corresponding to other people. Moreover, the photographs are taken in the wild with large variety in poses and expressions. We propose a novel method, Face Association through Model Evolution (FAME), that is able to prune the data in an iterative way, for the models associated to a name to evolve. The idea is based on capturing discriminative and representative properties of each instance and eliminating the outliers. The final models are used to classify faces on novel datasets with different characteristics. On benchmark datasets, our results are comparable to or better than the state-of-the-art studies for the task of face identification. © 2015 IEEE.
Open Access
Hypergraph-theoretic partitioning models for parallel web crawling
(Springer, London, 2012) Türk, Ata; Cambazoğlu, B. Barla; Aykanat, Cevdet
Parallel web crawling is an important technique employed by large-scale search engines for content acquisition. A commonly used inter-processor coordination scheme in parallel crawling systems is the link exchange scheme, where discovered links are communicated between processors. This scheme can attain the coverage and quality level of a serial crawler while avoiding redundant crawling of pages by different processors. The main problem in the exchange scheme is the high inter-processor communication overhead. In this work, we propose a hypergraph model that reduces the communication overhead associated with link exchange operations in parallel web crawling systems by intelligent assignment of sites to processors. Our hypergraph model can correctly capture and minimize the number of network messages exchanged between crawlers. We evaluate the performance of our models on four benchmark datasets. Compared to the traditional hash-based assignment approach, significant performance improvements are observed in reducing the inter-processor communication overhead. © 2012 Springer-Verlag London Limited.