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 fine-grained differences between them) and ignored for measuring similarity between the two images. Notably, while prior methods of using attribute annotations are often unable to outperform prior art, PAN obtains a 4-9% improvement on compatibility prediction between clothing items on Polyvore Outfits, a 5% gain on few shot classification of images using Caltech-UCSD Birds (CUB), and over 1% boost to Recall@1 on In-Shop Clothes Retrieval. Implementation available at https://github.com/samarth4149/PAN

翻译：测量两个图像之间的相似性往往需要在不同轴线(例如,颜色、纹理或形状)上进行复杂的推理。仔细观察对测量相似性可能很重要的东西可以通过附加说明的属性来提供,但先前的工作倾向于将这些注释视为完整的,从而导致它们使用简单的方法对单个图像的属性进行预测,而这些图像又被用来测量相似性。然而,数据集完全说明两个重要属性是不切实际的。因此,仅代表基于这些不完整的注释的图像可能错失关键信息。为解决这一问题,我们建议建立对测量相似性可能很重要的Pairwith 属性知情相似性网络(PAN),它打破相似性学习,从两个图像的共同表示中获取相似性条件和关联性评分。这使我们的模型能够识别两个图像包含相同的属性,但可以认为它们不相干(例如,由于它们之间的细微差异)和在测量两个图像之间的相似性差时被忽略。 值得注意的是,先前使用属性说明的方法往往无法超越先前的艺术, Pai- IPAN 将一个类似性学习到 ASU- re- bromailal- slial slial slial sal sal sal sal sal sal sal sal sal sal sal sal imlivial sal sal imviewal sal sal sal sal silviewal sal sal sal silps silps silps silviewal laps viewal viewal sqolgal sal sal vial sal silps sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sildal sildal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sal sil