all AI news
HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions. (arXiv:2207.14284v1 [cs.CV])
July 29, 2022, 1:12 a.m. | Yongming Rao, Wenliang Zhao, Yansong Tang, Jie Zhou, Ser-Nam Lim, Jiwen Lu
cs.CV updates on arXiv.org arxiv.org
Recent progress in vision Transformers exhibits great success in various
tasks driven by the new spatial modeling mechanism based on dot-product
self-attention. In this paper, we show that the key ingredients behind the
vision Transformers, namely input-adaptive, long-range and high-order spatial
interactions, can also be efficiently implemented with a convolution-based
framework. We present the Recursive Gated Convolution
($\textit{g}^\textit{n}$Conv) that performs high-order spatial interactions
with gated convolutions and recursive designs. The new operation is highly
flexible and customizable, which is compatible …
More from arxiv.org / cs.CV updates on arXiv.org
Jobs in AI, ML, Big Data
Software Engineer for AI Training Data (School Specific)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Python)
@ G2i Inc | Remote
Software Engineer for AI Training Data (Tier 2)
@ G2i Inc | Remote
Data Engineer
@ Lemon.io | Remote: Europe, LATAM, Canada, UK, Asia, Oceania
Artificial Intelligence – Bioinformatic Expert
@ University of Texas Medical Branch | Galveston, TX
Lead Developer (AI)
@ Cere Network | San Francisco, US