**Fastformer** is an type of [Transformer](https://paperswithcode.com/method/transformer) which uses [additive attention](https://www.paperswithcode.com/method/additive-attention) as a building block. Instead of modeling the pair-wise interactions between tokens, [additive attention](https://paperswithcode.com/method/additive-attention) is used to model global contexts, and then each token representation is further transformed based on its interaction with global context representations.

**PQ-Transformer**, or **PointQuad-Transformer**, is a [Transformer](https://paperswithcode.com/method/transformer)-based architecture that predicts 3D objects and layouts simultaneously, using point cloud inputs. Unlike existing methods that either estimate layout keypoints or edges, room layouts are directly parameterized as a set of quads. Along with the quad representation, a physical constraint loss function is used that discourages object-layout interference.

Given an input 3D point cloud of $N$ points, the point cloud feature learning backbone extracts $M$ context-aware point features of $\left(3+C\right)$ dimensions, through sampling and grouping. A voting module and a farthest point sampling (FPS) module are used to generate $K\_{1}$ object proposals and $K\_{2}$ quad proposals respectively. Then the proposals are processed by a transformer decoder to further refine proposal features. Through several feedforward layers and non-maximum suppression (NMS), the proposals become the final object bounding boxes and layout quads.

PQ-Transformer

PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds

Fastformer

Fastformer: Additive Attention Can Be All You Need

**Rainbow DQN** is an extended [DQN](https://paperswithcode.com/method/dqn) that combines several improvements into a single learner. Specifically:

- It uses [Double Q-Learning](https://paperswithcode.com/method/double-q-learning) to tackle overestimation bias.
- It uses [Prioritized Experience Replay](https://paperswithcode.com/method/prioritized-experience-replay) to prioritize important transitions.
- It uses [dueling networks](https://paperswithcode.com/method/dueling-network).
- It uses [multi-step learning](https://paperswithcode.com/method/n-step-returns).
- It uses distributional reinforcement learning instead of the expected return.
- It uses noisy linear layers for exploration.

Source	Fastformer: Additive Attention Can Be All You Need
Year	2000
Data Source	CC BY-SA - https://paperswithcode.com