Abstract | ||
---|---|---|
In recent years, deep-networks-based hashing has become a leading approach for large-scale image retrieval. Most deep hashing approaches use the high layer to extract the powerful semantic representations. However, these methods have limited ability for fine-grained image retrieval because the semantic features extracted from the high layer are difficult in capturing the subtle differences. To this end, we propose a novel two-pyramid hashing architecture to learn both the semantic information and the subtle appearance details for fine-grained image search. Inspired by the feature pyramids of convolutional neural network, avertical pyramid is proposed to capture the high-layer features and ahorizontal pyramid combines multiple low-layer features with structural information to capture the subtle differences. To fuse the low-level features, a novel combination strategy, called consensus fusion, is proposed to capture all subtle information from several low-layers for finer retrieval. Extensive evaluation on two fine-grained datasets CUB-200-2011 and Stanford Dogs demonstrate that the proposed method achieves significant performance compared with the state-of-art baselines.
|
Year | DOI | Venue |
---|---|---|
2019 | 10.1145/3323873.3325015 | ICMR '19: International Conference on Multimedia Retrieval
Ottawa ON
Canada
June, 2019 |
Keywords | DocType | Volume |
Image retrieval, Deep Hashing, Feature Pyramid | Conference | abs/1904.02325 |
ISBN | Citations | PageRank |
978-1-4503-6765-3 | 3 | 0.37 |
References | Authors | |
11 | 5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yifan Yang | 1 | 61 | 18.81 |
Libing Geng | 2 | 6 | 1.42 |
Hanjiang Lai | 3 | 234 | 17.67 |
Yan Pan | 4 | 179 | 19.23 |
Jian Yin | 5 | 861 | 97.01 |