** Spatial Pyramid Pooling (SPP)** is a pooling layer that removes the fixed-size constraint of the network, i.e. a CNN does not require a fixed-size input image. Specifically, we add an SPP layer on top of the last convolutional layer. The SPP layer pools the features and generates fixed-length outputs, which are then fed into the fully-connected layers (or other classifiers). In other words, we perform some information aggregation at a deeper stage of the network hierarchy (between convolutional layers and fully-connected layers) to avoid the need for cropping or warping at the beginning.

**Batchboost** is a variation on [MixUp](https://paperswithcode.com/method/mixup) that instead of mixing just two images, mixes many images together.

Batchboost

batchboost: regularization for stabilizing training with resistance to underfitting & overfitting

Spatial Pyramid Pooling

Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition

**Latent Optimisation** is a technique used for generative adversarial networks to refine the sample quality of $z$. Specifically, it exploits knowledge from the discriminator $D$ to refine the latent source $z$. Intuitively, the gradient $\nabla\_{z}f\left(z\right) = \delta{f}\left(z\right)\delta{z}$ points in the direction that better satisfies the discriminator $D$, which implies better samples. Therefore, instead of using the randomly sampled $z \sim p\left(z\right)$, we uses the optimised latent:

$$ \Delta{z} = \alpha\frac{\delta{f}\left(z\right)}{\delta{z}} $$

$$ z' = z + \Delta{z} $$

Source: [LOGAN](https://paperswithcode.com/method/logan)
.

Source	Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com