**SqueezeNet** is a convolutional neural network that employs design strategies to reduce the number of parameters, notably with the use of fire modules that "squeeze" parameters using 1x1 convolutions.

A wavelet **scattering transform** computes a translation invariant representation, which is stable to deformation, using a deep [convolution](https://paperswithcode.com/method/convolution) network architecture. It computes non-linear invariants with modulus and averaging pooling functions. It helps to eliminate the image variability due to translation and is stable to deformations. 

Image source: [Bruna and Mallat](https://arxiv.org/pdf/1203.1513v2.pdf)

ScatNet

Invariant Scattering Convolution Networks

SqueezeNet

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size

**GHM-R** is a loss function designed to balance the gradient flow for bounding box refinement. The GHM first performs statistics on the number of examples with similar attributes w.r.t their gradient density and then attaches a harmonizing parameter to the gradient of each example according to the density. The modification of gradient can be equivalently implemented by reformulating the loss function. Embedding the GHM into the bounding box regression branch is denoted as GHM-R loss.

Source	SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com