Abstract | ||
---|---|---|
In the well-known Bag-of-Words model, local features, such as the SIFT descriptor, are extracted and quantized into visual words. Then, an index is created to reduce computational burden. However, local clues serve as low-level representations that can not represent high-level semantic concepts. Recently, the success of deep features extracted from convolutional neural networks(CNN) has shown promising results toward bridging the semantic gap. Inspired by this, we attempt to introduce deep features into inverted index based image retrieval and thus propose the DeepIndex framework. Moreover, considering the compensation of different deep features, we incorporate multiple deep features from different fully connected layers, resulting in the multiple DeepIndex. We find the optimal integration of one midlevel deep feature and one high-level deep feature, from two different CNN architectures separately. This can be treated as an attempt to further reduce the semantic gap. Extensive experiments on three benchmark datasets demonstrate that, the proposed DeepIndex method is competitive with the state-of-the-art on Holidays(85:65% mAP), Paris(81:24% mAP), and UKB(3:76 score). In addition, our method is efficient in terms of both memory and time cost. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1145/2671188.2749300 | ICMR |
Keywords | Field | DocType |
Image Retrieval, Convolutional Neural Networks, Bag of Deep Features, DeepIndex | Inverted index,Data mining,Scale-invariant feature transform,Pattern recognition,Convolutional neural network,Computer science,Bridging (networking),Semantic gap,Image retrieval,Artificial intelligence,Machine learning,Visual Word | Conference |
Citations | PageRank | References |
13 | 0.51 | 27 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yu Liu | 1 | 198 | 25.45 |
Yanming Guo | 2 | 128 | 13.06 |
Song Wu | 3 | 90 | 5.58 |
Michael S. Lew | 4 | 2742 | 166.02 |