Compression Of Deep Neural Networks For Image Instance Retrieval

Abstract

Image instance retrieval is the problem of retrieving images from a database which contain the same object. Convolutional Neural Network (CNN) based descriptors are becoming the dominant approach for generating \{\it global image descriptors\} for the instance retrieval problem. One major drawback of CNN-based \{\it global descriptors\} is that uncompressed deep neural network models require hundreds of megabytes of storage making them inconvenient to deploy in mobile applications or in custom hardware. In this work, we study the problem of neural network model compression focusing on the image instance retrieval task. We study quantization, coding, pruning and weight sharing techniques for reducing model size for the instance retrieval problem. We provide extensive experimental results on the trade-off between retrieval performance and model size for different types of networks on several data sets providing the most comprehensive study on this topic. We compress models to the order o

Stats

• citations14
• S2 citations—
• github stars0
• HF likes0
• heat score8.82
• arxiv keychandrasekhar2017compression

Related papers

• Pruning Convolutional Neural Networks For Image Instance Retrieval (2017)0.00
• Group Invariant Deep Representations For Image Instance Retrieval (2016)0.00
• From Selective Deep Convolutional Features To Compact Binary Representations For Image Retrieval (2018)10.35
• What Is The Best Practice For Cnns Applied To Visual Instance Retrieval? (2016)0.00
• Deep Image Retrieval: Learning Global Representations For Image Search (2016)19.67
• Class-weighted Convolutional Features For Visual Instance Search (2017)12.81
• Deep Learning For Instance Retrieval: A Survey (2021)16.05
• Compressible And Searchable: Ai-native Multi-modal Retrieval System With Learned Image Compression (2024)0.00