A Fixed-Point Approach to Unified Prompt-Based Counting
Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (4) · 3468-3476
DOI: 10.1609/aaai.v38i4.28134 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Wei Lin und 1 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
Existing class-agnostic counting models typically rely on a single type of prompt, e.g., box annotations. This paper aims to establish a comprehensive prompt-based counting framework capable of generating density maps for concerned objects indicated by various prompt types, such as box, point, and text. To achieve this goal, we begin by converting prompts from different modalities into prompt masks without requiring training. These masks are then integrated into a class-agnostic counting methodology for predicting density maps. Furthermore, we introduce a fixed-point inference along with an associated loss function to improve counting accuracy, all without introducing new parameters. The effectiveness of this method is substantiated both theoretically and experimentally. Additionally, a contrastive training scheme is implemented to mitigate dataset bias inherent in current class-agnostic counting datasets, a strategy whose effectiveness is confirmed by our ablation study. Our model excels in prominent class-agnostic datasets and exhibits superior performance in cross-dataset adaptation tasks.
Zitieren
APA
Lin, W., & Chan, A. B. (2024). A Fixed-Point Approach to Unified Prompt-Based Counting. Proceedings of the AAAI Conference on Artificial Intelligence, 38(4), 3468-3476. https://doi.org/10.1609/aaai.v38i4.28134
Vancouver
Lin W, Chan AB. A Fixed-Point Approach to Unified Prompt-Based Counting. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(4):3468-3476. doi:10.1609/aaai.v38i4.28134
BibTeX
@article{Lin2024,
author = {Lin, Wei and Chan, Antoni B.},
title = {A Fixed-Point Approach to Unified Prompt-Based Counting},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2024},
volume = {38},
number = {4},
pages = {3468--3476},
doi = {10.1609/aaai.v38i4.28134}
}
EUVIMED