CVLGIVMar 30, 2020

Co-occurrence of deep convolutional features for image search

arXiv:2003.13827v223 citations
Originality Incremental advance
AI Analysis

This work addresses image retrieval for computer vision applications, presenting an incremental improvement over existing methods.

The paper tackles image search by proposing a new co-occurrence representation of deep convolutional features to enhance image descriptors, achieving improved performance on well-known image retrieval datasets.

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.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes