Image Models


Introduced by Sandler et al. in MobileNetV2: Inverted Residuals and Linear Bottlenecks

MobileNetV2 is a convolutional neural network architecture that seeks to perform well on mobile devices. It is based on an inverted residual structure where the residual connections are between the bottleneck layers. The intermediate expansion layer uses lightweight depthwise convolutions to filter features as a source of non-linearity. As a whole, the architecture of MobileNetV2 contains the initial fully convolution layer with 32 filters, followed by 19 residual bottleneck layers.

Source: MobileNetV2: Inverted Residuals and Linear Bottlenecks


Paper Code Results Date Stars


Task Papers Share
Image Classification 55 12.11%
Object Detection 45 9.91%
Quantization 44 9.69%
Semantic Segmentation 25 5.51%
Classification 17 3.74%
General Classification 15 3.30%
Model Compression 14 3.08%
Instance Segmentation 8 1.76%
Benchmarking 7 1.54%