The **NVAE Generative Residual Cell** is a skip connection block used as part of the [NVAE](https://paperswithcode.com/method/nvae) architecture for the generator. The residual cell expands the number of channels $E$ times before applying the [depthwise separable convolution](https://paperswithcode.com/method/depthwise-separable-convolution), and then maps it back to $C$ channels. The design motivation was to help model long-range correlations in the data by increasing the receptive field of the network, which explains the expanding path but also the use of depthwise convolutions to keep a handle on parameter count.

**IoU-Balanced Sampling** is hard mining method for object detection. Suppose we need to sample $N$ negative samples from $M$ corresponding candidates. The selected probability for each sample under random sampling is:

$$ p = \frac{N}{M} $$

To raise the selected probability of hard negatives, we evenly split the sampling interval into $K$ bins according to IoU. $N$ demanded negative samples are equally distributed to each bin. Then we select samples from them uniformly. Therefore, we get the selected probability under IoU-balanced sampling:

$$ p\_{k} = \frac{N}{K}*\frac{1}{M\_{k}}\text{ , } k\in\left[0, K\right)$$

where $M\_{k}$ is the number of sampling candidates in the corresponding interval denoted by $k$. $K$ is set to 3 by default in our experiments.

The sampled histogram with IoU-balanced sampling is shown by green color in the Figure to the right. The IoU-balanced sampling can guide the distribution of training samples close to the one of hard negatives.

IoU-Balanced Sampling

Libra R-CNN: Towards Balanced Learning for Object Detection

NVAE Generative Residual Cell

NVAE: A Deep Hierarchical Variational Autoencoder

**IFNet** is an architecture for video frame interpolation that adopts a coarse-to-fine strategy with progressively increased resolutions: it iteratively updates intermediate flows and soft fusion mask via successive [IFBlocks](https://paperswithcode.com/method/ifblock). Conceptually, according to the iteratively updated flow fields, we can move corresponding pixels from two input frames to the same location in a latent intermediate frame and use a fusion mask to combine pixels from two input frames. Unlike most previous optical flow models, IFBlocks do not contain expensive operators like cost volume or forward warping and use 3 × 3 [convolution](https://paperswithcode.com/method/convolution) and deconvolution as building blocks.

Source	NVAE: A Deep Hierarchical Variational Autoencoder
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com