Return to search

The "What"-"Where" Network: A Tool for One-Shot Image Recognition and Localization

One common shortcoming of modern computer vision is the inability of most models to generalize to new classes—one/few shot image recognition. We propose a new problem formulation for this task and present a network architecture and training methodology to solve this task. Further, we provide insights into how careful focus on how not just the data, but the way data presented to the model can have significant impact on performance. Using these method, we achieve high accuracy in few-shot image recognition tasks.

Identiferoai:union.ndltd.org:BGMYU2/oai:scholarsarchive.byu.edu:etd-10375
Date06 January 2021
CreatorsHurlburt, Daniel
PublisherBYU ScholarsArchive
Source SetsBrigham Young University
Detected LanguageEnglish
Typetext
Formatapplication/pdf
SourceTheses and Dissertations
Rightshttps://lib.byu.edu/about/copyright/

Page generated in 0.0019 seconds