Selective Deep Convolutional Features for Image Retrieval
Convolutional Neural Network (CNN) is a very powerful approach to extract discriminative local descriptors for effective image search. Recent work adopts fine-tuned strategies to further improve the discriminative power of the descriptors. Taking a different approach, in this paper, we propose a novel framework to achieve competitive retrieval performance. Firstly, we propose various masking schemes, namely SIFT-mask, SUM-mask, and MAX-mask, to select a representative subset of local convolutional features and remove a large number of redundant features. We demonstrate that this can effectively address the burstiness issue and improve retrieval accuracy. Secondly, we propose to employ recent embedding and aggregating methods to further enhance feature discriminability. Extensive experiments demonstrate that our proposed framework achieves state-of-the-art retrieval accuracy.
Code (1)
Tasks
Image RetrievalRetrievalSimilar Papers 제목 키워드 기반
Selective Convolutional Descriptor Aggregation for Fine-Grained Image Retrieval
Deep convolutional neural network models pre-trained for the ImageNet classification task have been successfully adopted to tasks in other domains, such as texture description and object proposal generation, but these ta…
Image RetrievalObject Proposal GenerationRetrievalFrom Selective Deep Convolutional Features to Compact Binary Representations for Image Retrieval
In the large-scale image retrieval task, the two most important requirements are the discriminability of image representations and the efficiency in computation and storage of representations. Regarding the former requir…
Image RetrievalRetrievalExploiting Local Features from Deep Networks for Image Retrieval
Deep convolutional neural networks have been successfully applied to image classification tasks. When these same networks have been applied to image retrieval, the assumption has been made that the last layers would give…
ClassificationGeneral Classificationimage-classificationImage Classification+2View-GCN: View-Based Graph Convolutional Network for 3D Shape Analysis
View-based approach that recognizes 3D shape through its projected 2D images has achieved state-of-the-art results for 3D shape recognition. The major challenge for view-based approach is how to aggregate multi-view feat…
3D Shape Classification3D Shape RecognitionRetrievalLocal Convolutional Features With Unsupervised Training for Image Retrieval
Patch-level descriptors underlie several important computer vision tasks, such as stereo-matching or content-based image retrieval. We introduce a deep convolutional architecture that yields patch-level descriptors, a…
Content-Based Image RetrievalImage RetrievalRetrievalStereo Matching+1