**Hybrid Task Cascade**, or **HTC**, is a framework for cascading in instance segmentation. It differs from [Cascade Mask R-CNN](https://paperswithcode.com/method/cascade-mask-r-cnn) in two important aspects:  (1) instead of performing cascaded refinement on the two tasks of detection and segmentation separately, it interweaves them for a joint multi-stage processing; (2) it adopts a fully convolutional branch to provide spatial context, which can help distinguishing hard foreground from cluttered background.

A **CoordConv** layer is a simple extension to the standard convolutional layer. It has the same functional signature as a convolutional layer, but accomplishes the mapping by first concatenating extra channels to the incoming representation. These channels contain hard-coded coordinates, the most basic version of which is one channel for the $i$ coordinate and one for the $j$ coordinate.

The CoordConv layer keeps the properties of few parameters and efficient computation from convolutions, but allows the network to learn to keep or to discard translation invariance as is needed for the task being learned. This is useful for coordinate transform based tasks where regular convolutions can fail.

CoordConv

An Intriguing Failing of Convolutional Neural Networks and the CoordConv Solution

Hybrid Task Cascade for Instance Segmentation

The **Hard Sigmoid** is an activation function used for neural networks of the form:

$$f\left(x\right) = \max\left(0, \min\left(1,\frac{\left(x+1\right)}{2}\right)\right)$$

Image Source: [Rinat Maksutov](https://towardsdatascience.com/deep-study-of-a-not-very-deep-neural-network-part-2-activation-functions-fd9bd8d406fc)

Source	Hybrid Task Cascade for Instance Segmentation
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com