Visualizing Deep Similarity Networks

Abstract

For convolutional neural network models that optimize an image embedding, we propose a method to highlight the regions of images that contribute most to pairwise similarity. This work is a corollary to the visualization tools developed for classification networks, but applicable to the problem domains better suited to similarity learning. The visualization shows how similarity networks that are fine-tuned learn to focus on different features. We also generalize our approach to embedding networks that use different pooling strategies and provide a simple mechanism to support image similarity searches on objects or sub-regions in the query image.

Stats

• citations37
• S2 citations—
• github stars0
• HF likes0
• heat score11.85
• arxiv keystylianou2019visualizing

Related papers

• Conditional Similarity Networks (2016)15.06
• Deepsim-nets: Deep Similarity Networks For Stereo Image Matching (2023)5.24
• Image Similarity Using Deep CNN And Curriculum Learning (2017)0.00
• Learning Non-metric Visual Similarity For Image Retrieval (2017)11.58
• Retrieving Similar E-commerce Images Using Deep Learning (2019)0.00
• Towards Visually Explaining Similarity Models (2020)0.00
• Local Similarity-aware Deep Feature Embedding (2016)0.00
• Visual Explanation For Deep Metric Learning (2019)14.36