A **Graph Convolutional Network**, or **GCN**, is an approach for semi-supervised learning on graph-structured data. It is based on an efficient variant of [convolutional neural networks](https://paperswithcode.com/methods/category/convolutional-neural-networks) which operate directly on graphs. The choice of convolutional architecture is motivated via a localized first-order approximation of spectral graph convolutions. The model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes.

**Mask R-CNN** extends [Faster R-CNN](http://paperswithcode.com/method/faster-r-cnn) to solve instance segmentation tasks. It achieves this by adding a branch for predicting an object mask in parallel with the existing branch for bounding box recognition. In principle, Mask R-CNN is an intuitive extension of Faster [R-CNN](https://paperswithcode.com/method/r-cnn), but constructing the mask branch properly is critical for good results. 

Most importantly, Faster R-CNN was not designed for pixel-to-pixel alignment between network inputs and outputs. This is evident in how [RoIPool](http://paperswithcode.com/method/roi-pooling), the *de facto* core operation for attending to instances, performs coarse spatial quantization for feature extraction. To fix the misalignment, Mask R-CNN utilises a simple, quantization-free layer, called [RoIAlign](http://paperswithcode.com/method/roi-align), that faithfully preserves exact spatial locations. 

Secondly, Mask R-CNN *decouples* mask and class prediction: it predicts a binary mask for each class independently, without competition among classes, and relies on the network's RoI classification branch to predict the category. In contrast, an [FCN](http://paperswithcode.com/method/fcn) usually perform per-pixel multi-class categorization, which couples segmentation and classification.

Mask R-CNN

Semi-Supervised Classification with Graph Convolutional Networks

A **Denoising Autoencoder** is a modification on the [autoencoder](https://paperswithcode.com/method/autoencoder) to prevent the network learning the identity function. Specifically, if the autoencoder is too big, then it can just learn the data, so the output equals the input, and does not perform any useful representation learning or dimensionality reduction. Denoising autoencoders solve this problem by corrupting the input data on purpose, adding noise or masking some of the input values.

Image Credit: [Kumar et al](https://www.semanticscholar.org/paper/Static-hand-gesture-recognition-using-stacked-Kumar-Nandi/5191ddf3f0841c89ba9ee592a2f6c33e4a40d4bf)

Source	Semi-Supervised Classification with Graph Convolutional Networks
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com