A Transformer is a model architecture that eschews recurrence and instead relies entirely on an attention mechanism to draw global dependencies between input and output. Before Transformers, the dominant sequence transduction models were based on complex recurrent or convolutional neural networks that include an encoder and a decoder. The Transformer also employs an encoder and decoder, but removing recurrence in favor of attention mechanisms allows for significantly more parallelization than methods like RNNs and CNNs.
Absolute Position Encodings are a type of position embeddings for [Transformer-based models] where positional encodings are added to the input embeddings at the bottoms of the encoder and decoder stacks. The positional encodings have the same dimension $d\_{model}$ as the embeddings, so that the two can be summed. In the original implementation, sine and cosine functions of different frequencies are used: $$ \text{PE}\left(pos, 2i\right) = \sin\left(pos/10000^{2i/d\_{model}}\right) $$ $$ \text{PE}\left(pos, 2i+1\right) = \cos\left(pos/10000^{2i/d\_{model}}\right) $$ where $pos$ is the position and $i$ is the dimension. That is, each dimension of the positional encoding corresponds to a sinusoid. The wavelengths form a geometric progression from $2\pi$ to $10000 \dot 2\pi$. This function was chosen because the authors hypothesized it would allow the model to easily learn to attend by relative positions, since for any fixed offset $k$, $\text{PE}\_{pos+k}$ can be represented as a linear function of $\text{PE}\_{pos}$. Image Source: D2L.ai
PolyConv learns continuous distributions as the convolutional filters to share the weights across different vertices of graphs or points of point clouds.
Anisotropic convolution is a central building block of CNNs but challenging to transfer to surfaces. DeltaConv learns combinations and compositions of operators from vector calculus, which are a natural fit for curved surfaces. The result is a simple and robust anisotropic convolution operator for point clouds with state-of-the-art results.
PointASNL is a non-local neural network for point clouds processing It consists of two general modules: adaptive sampling (AS) module and local-Nonlocal (L-NL) module. The AS module first re-weights the neighbors around the initial sampled points from farthest point sampling (FPS), and then adaptively adjusts the sampled points beyond the entire point cloud. The AS module can not only benefit the feature learning of point clouds, but also ease the biased effect of outliers. The L-NL module capture the neighbor and long-range dependencies of the sampled point, and enables the learning process to be insensitive to noise.