all AI news
ProtoP-OD: Explainable Object Detection with Prototypical Parts
March 1, 2024, 5:43 a.m. | Pavlos Rath-Manakidis, Frederik Strothmann, Tobias Glasmachers, Laurenz Wiskott
cs.LG updates on arXiv.org arxiv.org
Abstract: Interpretation and visualization of the behavior of detection transformers tends to highlight the locations in the image that the model attends to, but it provides limited insight into the \emph{semantics} that the model is focusing on. This paper introduces an extension to detection transformers that constructs prototypical local features and uses them in object detection. These custom features, which we call prototypical parts, are designed to be mutually exclusive and align with the classifications of …
abstract arxiv behavior cs.cv cs.lg detection extension highlight image insight interpretation locations paper semantics transformers type visualization
More from arxiv.org / cs.LG updates on arXiv.org
The Perception-Robustness Tradeoff in Deterministic Image Restoration
2 days, 16 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
Founding AI Engineer, Agents
@ Occam AI | New York
AI Engineer Intern, Agents
@ Occam AI | US
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne