Get the latest tech news
DreamSim: Learning New Dimensions of Human Visual Similarity (2023)
We generate a new benchmark of synthetic image triplets that span a wide range of mid-level variations, labeled with human similarity judgments. The dots below each image indicate which image is considered most similar to the reference by humans vs several existing metrics and our new metric, DreamSim.
We generate a new benchmark of synthetic image triplets that span a wide range of mid-level variations, labeled with human similarity judgments. We analyze how our metric is affected by different visual attributes, and find that it focuses heavily on foreground objects and semantic content while also being sensitive to color and layout. @article{fu2024dreamsim, title={DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data}, author={Fu, Stephanie and Tamir, Netanel and Sundaram, Shobhita and Chai, Lucy and Zhang, Richard and Dekel, Tali and Isola, Phillip}, journal={Advances in Neural Information Processing Systems}, volume={36} year={2024} }
Or read this on Hacker News
