Co-occurrence Of Deep Convolutional Features For Image Search

Abstract

Image search can be tackled using deep features from pre-trained Convolutional Neural Networks (CNN). The feature map from the last convolutional layer of a CNN encodes descriptive information from which a discriminative global descriptor can be obtained. We propose a new representation of co-occurrences from deep convolutional features to extract additional relevant information from this last convolutional layer. Combining this co-occurrence map with the feature map, we achieve an improved image representation. We present two different methods to get the co-occurrence representation, the first one based on direct aggregation of activations, and the second one, based on a trainable co-occurrence representation. The image descriptors derived from our methodology improve the performance in very well-known image retrieval datasets as we prove in the experiments.

Stats

• citations19
• S2 citations—
• github stars0
• HF likes0
• heat score9.76
• arxiv keyforcen2020co

Related papers

• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• Unifying Deep Local And Global Features For Image Search (2020)28.10
• A Fast Content-based Image Retrieval Method Using Deep Visual Features (2019)6.77
• Class-weighted Convolutional Features For Visual Instance Search (2017)12.81
• Adaptive Co-weighting Deep Convolutional Features For Object Retrieval (2018)4.52
• What Is The Best Practice For Cnns Applied To Visual Instance Retrieval? (2016)0.00
• Simultaneous Feature Aggregating And Hashing For Large-scale Image Search (2017)10.61