**Discriminative Regularization** is a regularization technique for [variational autoencoders](https://paperswithcode.com/methods/category/likelihood-based-generative-models) that uses representations from discriminative classifiers to augment the [VAE](https://paperswithcode.com/method/vae) objective function (the lower bound) corresponding to a generative model. Specifically, it encourages the model’s reconstructions to be close to the data example in a representation space defined by the hidden layers of highly-discriminative, neural network based classifiers.

**Adaptive Training Sample Selection**, or **ATSS**, is a method to automatically select positive and negative samples according to statistical characteristics of object. It bridges the gap between anchor-based and anchor-free detectors. 

For each ground-truth box $g$ on the image, we first find out its candidate positive samples. As described in Line $3$ to $6$, on each pyramid level, we select $k$ anchor boxes whose center are closest to the center of $g$ based on L2 distance. Supposing there are $\mathcal{L}$ feature pyramid levels, the ground-truth box $g$ will have $k\times\mathcal{L}$ candidate positive samples. After that, we compute the IoU between these candidates and the ground-truth $g$ as $\mathcal{D}_g$ in Line $7$, whose mean and standard deviation are computed as $m_g$ and $v_g$ in Line $8$ and Line $9$. With these statistics, the IoU threshold for this ground-truth $g$ is obtained as $t_g=m_g+v_g$ in Line $10$. Finally, we select these candidates whose IoU are greater than or equal to the threshold $t_g$ as final positive samples in Line $11$ to $15$. 

Notably ATSS also limits the positive samples' center to the ground-truth box as shown in Line $12$. Besides, if an anchor box is assigned to multiple ground-truth boxes, the one with the highest IoU will be selected. The rest are negative samples.

ATSS

Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection

Discriminative Regularization

Discriminative Regularization for Generative Models

**StyleMapGAN** is a generative adversarial network for real-time image editing. The intermediate latent space has spatial dimensions, and a spatially variant modulation replaces [AdaIN](https://paperswithcode.com/method/adaptive-instance-normalization). It aims to make the embedding through an encoder more accurate than existing optimization-based methods while maintaining the properties of GANs.

Source	Discriminative Regularization for Generative Models
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com