Pruning Convolutional Neural Networks for Image Instance Retrieval
This work addresses efficiency in image retrieval for applications requiring lightweight models, but it is incremental as it builds on existing pruning and fine-tuning techniques.
The paper tackles the problem of compressing Convolutional Neural Networks for image instance retrieval by pruning convolutional edges, achieving a 5x compression rate with minimal loss in retrieval performance through a combination of heuristic pruning and fine-tuning.
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.