Summary of Evidential Transformers For Improved Image Retrieval, by Danilo Dordevic et al.
Evidential Transformers for Improved Image Retrieval
by Danilo Dordevic, Suryansh Kumar
First submitted to arxiv on: 2 Sep 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Information Retrieval (cs.IR); Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The Evidential Transformer is an uncertainty-driven transformer model that improves and robustifies image retrieval. By incorporating probabilistic methods into content-based image retrieval (CBIR), this model achieves reliable results, outperforming traditional training based on multiclass classification as a baseline for deep metric learning. The Global Context Vision Transformer (GC ViT) architecture also helps to improve state-of-the-art retrieval results on several datasets, including the Stanford Online Products (SOP) and CUB-200-2011 datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The Evidential Transformer is a new way to find images based on what they look like. It uses special math to make sure it gets the right answer most of the time. This helps when we’re searching for pictures in really big collections. The model works better than usual methods, and it even beats other ways that are already good at finding images. |
Keywords
» Artificial intelligence » Classification » Transformer » Vision transformer » Vit
