论文标题
群体模棱两可的独立自我关注
Group Equivariant Stand-Alone Self-Attention For Vision
论文作者
论文摘要
我们提供了一种一般的自我注意事项，以将群体均衡为任意对称群体。这是通过定义对小组所考虑的行动不变的位置编码来实现的。由于该小组直接对位置编码进行作用，因此本质上是群体模棱两可的自我发场网络（GSA-NET）。我们对视觉基准测试的实验表明，GSA网络对非等级的自我发项网络的一致改进。
We provide a general self-attention formulation to impose group equivariance to arbitrary symmetry groups. This is achieved by defining positional encodings that are invariant to the action of the group considered. Since the group acts on the positional encoding directly, group equivariant self-attention networks (GSA-Nets) are steerable by nature. Our experiments on vision benchmarks demonstrate consistent improvements of GSA-Nets over non-equivariant self-attention networks.
