AutoML

Shape Adaptor

Introduced by Liu et al. in Shape Adaptor: A Learnable Resizing Module

Shape Adaptor is a novel resizing module for neural networks. It is a drop-in enhancement built on top of traditional resizing layers, such as pooling, bilinear sampling, and strided convolution. This module allows for a learnable shaping factor which differs from the traditional resizing layers that are fixed and deterministic.

Image Source: Liu et al.

Source: Shape Adaptor: A Learnable Resizing Module

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Image Classification 2 100.00%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories