iNL: Implicit non-local network

The attention mechanism of computer vision represented by a non-local network improves the performance of numerous vision tasks while bringing computational burden for deployment Wang et al. (2018). In this work, we explore to release the inference computation for non-local network by decoupling the...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Neurocomputing (Amsterdam) Ročník 482; s. 50 - 59
Hlavní autori: Han, Yifeng, Chen, Xi, Zhang, Songjie, Qi, Donglian
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Elsevier B.V 14.04.2022
Predmet:
Attention
Computation cost
Generalized form
Implicit method
Computation cost
Implicit method
Generalized form
Attention
ISSN:0925-2312, 1872-8286
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Popis
Shrnutí:The attention mechanism of computer vision represented by a non-local network improves the performance of numerous vision tasks while bringing computational burden for deployment Wang et al. (2018). In this work, we explore to release the inference computation for non-local network by decoupling the training/inference procedure. Specifically, we propose the implicit non-local network (iNL). During training, iNL models the dependency between features across long-range affinities like original non-local blocks; during inference, iNL could be reformulated as only two convolution layers but can rival non-local network. In this way, the computation complexity and the memory costs are reduced. In addition, we take a further step and extend our iNL into a more generalized form, which covers the attentions of different orders in computer vision tasks. iNL brings steady improvements on multiple benchmarks of different vision tasks including classification, detection, and instance segmentation. In the meantime, it provides a brand–new perspective to understand the attention mechanism in deep neural networks.
ISSN:0925-2312
1872-8286
DOI:10.1016/j.neucom.2022.01.047