**BlendMask** is an [instance segmentation framework](https://paperswithcode.com/methods/category/instance-segmentation-models) built on top of the[ FCOS](https://paperswithcode.com/method/fcos) object detector. The bottom module uses either backbone or [FPN](https://paperswithcode.com/method/fpn) features to predict a set of bases. A single [convolution](https://paperswithcode.com/methods/category/convolutions) layer is added on top of the detection towers to produce attention masks along with each bounding box prediction. For each predicted instance, the [blender](https://paperswithcode.com/method/blender) crops the bases with its bounding box and linearly combine them according the learned attention maps. Note that the Bottom Module can take features either from ‘C’, or ‘P’ as the input.

**Faster R-CNN** is an object detection model that improves on [Fast R-CNN](https://paperswithcode.com/method/fast-r-cnn) by utilising a region proposal network ([RPN](https://paperswithcode.com/method/rpn)) with the CNN model. The RPN shares full-image convolutional features with the detection network, enabling nearly cost-free region proposals. It is a fully convolutional network that simultaneously predicts object bounds and objectness scores at each position. The RPN is trained end-to-end to generate high-quality region proposals, which are used by [Fast R-CNN](https://paperswithcode.com/method/fast-r-cnn) for detection. RPN and Fast [R-CNN](https://paperswithcode.com/method/r-cnn) are merged into a single network by sharing their convolutional features: the RPN component tells the unified network where to look.

As a whole, Faster R-CNN consists of two modules. The first module is a deep fully convolutional network that proposes regions, and the second module is the Fast R-CNN detector that uses the proposed regions.

Faster R-CNN

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

BlendMask

BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation

In a **Replacing Eligibility Trace**, each time the state is revisited, the trace is reset to $1$ regardless of the presence of a prior trace.. For the memory vector $\textbf{e}\_{t} \in \mathbb{R}^{b} \geq \textbf{0}$:

$$\mathbf{e\_{0}} = \textbf{0}$$

$$\textbf{e}\_{t} = \gamma\lambda{e}\_{t-1}\left(s\right) \text{ if } s \neq s\_{t}$$

$$\textbf{e}\_{t} = 1 \text{ if } s = s\_{t}$$

They can be seen as crude approximation to dutch traces, which have largely superseded them as they perform better than replacing traces and have a clearer theoretical basis. Accumulating traces remain of interest for nonlinear function approximations where dutch traces are not available.

Source: Sutton and Barto, Reinforcement Learning, 2nd Edition

Source	BlendMask: Top-Down Meets Bottom-Up for Instance Segmentation
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com