Pruning Convolutional Neural Networks for Image Instance Retrieval

Abstract

In this work, we focus on the problem of image instance retrieval with deep descriptors extracted from pruned Convolutional Neural Networks (CNN). The objective is to heavily prune convolutional edges while maintaining retrieval performance. To this end, we introduce both data-independent and data-dependent heuristics to prune convolutional edges, and evaluate their performance across various compression rates with different deep descriptors over several benchmark datasets. Further, we present an end-to-end framework to fine-tune the pruned network, with a triplet loss function specially designed for the retrieval task. We show that the combination of heuristic pruning and fine-tuning offers 5x compression rate without considerable loss in retrieval performance.

arXiv comment5 pages

References in corpus (5)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Exploiting Linear Structure Within Convolutional Networks for Efficient Evaluation
• Pruning Convolutional Neural Networks for Resource Efficient Inference
• Group Invariant Deep Representations for Image Instance Retrieval