Effectively Leveraging Attributes For Visual Similarity

Abstract

Measuring similarity between two images often requires performing complex reasoning along different axes (e.g., color, texture, or shape). Insights into what might be important for measuring similarity can can be provided by annotated attributes, but prior work tends to view these annotations as complete, resulting in them using a simplistic approach of predicting attributes on single images, which are, in turn, used to measure similarity. However, it is impractical for a dataset to fully annotate every attribute that may be important. Thus, only representing images based on these incomplete annotations may miss out on key information. To address this issue, we propose the Pairwise Attribute-informed similarity Network (PAN), which breaks similarity learning into capturing similarity conditions and relevance scores from a joint representation of two images. This enables our model to identify that two images contain the same attribute, but can have it deemed irrelevant (e.g., due to fin

Stats

• citations1
• S2 citations—
• github stars4
• HF likes0
• heat score3.66
• arxiv keymishra2021effectively

Related papers

• Attributable Visual Similarity Learning (2022)11.68
• Visualizing Deep Similarity Networks (2019)11.85
• Conditional Similarity Networks (2016)15.06
• Fine-grained Fashion Similarity Prediction By Attribute-specific Embedding Learning (2021)15.29
• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Visual Similarity Attention (2019)0.00
• Compare More Nuanced:pairwise Alignment Bilinear Network For Few-shot Fine-grained Learning (2019)11.39
• Represent, Compare, And Learn: A Similarity-aware Framework For Class-agnostic Counting (2022)14.58