Incorporating Side Information by Adaptive Convolution

87 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Dynamic Neural Networks: A Survey (2021, neutral): “graph convolution, and camera perspective is incorporated in [122] to generate weights for image convolution.”
Adaptive Convolution for Multi-Relational Learning (2019, background): “Similar ideas of using adaptive or dynamic convolutional filters have been studied before (Lee et al., 2010; Jia et al., 2016; Kang et al., 2017).”
Improved Techniques for Training Adaptive Deep Networks (2019, background): “ accuracy. Adaptive Inference. Recently, a new emerging direction which employs adaptive learning for efﬁcient inference has drawn increasing research attention, with representative works proposed in [14,2,25,35,19,6,24,38,36,29,37, 18]. Adaptive inference aims at achieving efﬁcient resource allocat”
Context-Aware Crowd Counting (2018, methodology): “For example, the algorithms of [41, 17] use geometric information to adapt the network to different scene geometries.”
Adaptive Convolution for Object Detection (2019, methodology): “other drawback of the methods in [27]–[29] is the limitation of model parameters.”