Description
ScaleNet, or a Scale Aggregation Network, is a type of convolutional neural network which learns a neuron allocation for aggregating multi-scale information in different building blocks of a deep network. The most informative output neurons in each block are preserved while others are discarded, and thus neurons for multiple scales are competitively and adaptively allocated. The scale aggregation (SA) block concatenates feature maps at a wide range of scales. Feature maps for each scale are generated by a stack of downsampling, convolution and upsampling operations.
Papers Using This Method
Scale Invariance of Graph Neural Networks2024-11-28ScaleNet: Scale Invariance Learning in Directed Graphs2024-11-13ScaleNet: An Unsupervised Representation Learning Method for Limited Information2023-10-03ScaleNet: Searching for the Model to Scale2022-07-15ScaleNet: A Shallow Architecture for Scale Estimation2021-12-09ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition2020-11-30Data-Driven Neuron Allocation for Scale Aggregation Networks2019-04-20