all AI news
A Simple-but-effective Baseline for Training-free Class-Agnostic Counting
March 5, 2024, 2:48 p.m. | Yuhao Lin, Haiming Xu, Lingqiao Liu, Javen Qinfeng Shi
cs.CV updates on arXiv.org arxiv.org
Abstract: Class-Agnostic Counting (CAC) seeks to accurately count objects in a given image with only a few reference examples. While previous methods achieving this relied on additional training, recent efforts have shown that it's possible to accomplish this without training by utilizing pre-existing foundation models, particularly the Segment Anything Model (SAM), for counting via instance-level segmentation. Although promising, current training-free methods still lag behind their training-based counterparts in terms of performance. In this research, we present …
abstract arxiv cac class count cs.cv examples foundation free image objects reference segment segment anything simple training type
More from arxiv.org / cs.CV updates on arXiv.org
Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs
1 day, 12 hours ago |
arxiv.org
Jobs in AI, ML, Big Data
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
Senior Machine Learning Engineer (MLOps)
@ Promaton | Remote, Europe
Global Data Architect, AVP - State Street Global Advisors
@ State Street | Boston, Massachusetts
Data Engineer
@ NTT DATA | Pune, MH, IN