Class-weighted Convolutional Features For Visual Instance Search

Abstract

Image retrieval in realistic scenarios targets large dynamic datasets of unlabeled images. In these cases, training or fine-tuning a model every time new images are added to the database is neither efficient nor scalable. Convolutional neural networks trained for image classification over large datasets have been proven effective feature extractors for image retrieval. The most successful approaches are based on encoding the activations of convolutional layers, as they convey the image spatial information. In this paper, we go beyond this spatial information and propose a local-aware encoding of convolutional features based on semantic information predicted in the target image. To this end, we obtain the most discriminative regions of an image using Class Activation Maps (CAMs). CAMs are based on the knowledge contained in the network and therefore, our approach, has the additional advantage of not requiring external information. In addition, we use CAMs to generate object proposals du

Stats

• citations50
• S2 citations—
• github stars0
• HF likes0
• heat score12.81
• arxiv keyjimenez2017class

Related papers

• Saliency Weighted Convolutional Features For Instance Search (2017)9.92
• What Is The Best Practice For Cnns Applied To Visual Instance Retrieval? (2016)0.00
• Where To Focus: Query Adaptive Matching For Instance Retrieval Using Convolutional Feature Maps (2016)0.00
• Faster R-CNN Features For Instance Search (2016)14.62
• Co-occurrence Of Deep Convolutional Features For Image Search (2020)9.76
• A Fast Content-based Image Retrieval Method Using Deep Visual Features (2019)6.77
• Class Agnostic Instance-level Descriptor For Visual Instance Search (2025)0.00
• Group Invariant Deep Representations For Image Instance Retrieval (2016)0.00