Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation. (arXiv:2207.10866v1 [cs.CV])

This paper presents a novel cost aggregation network, called Volumetric
Aggregation with Transformers (VAT), for few-shot segmentation. The use of
transformers can benefit correlation map aggregation through self-attention
over a global receptive field. However, the tokenization of a correlation map
for transformer processing can be detrimental, because the discontinuity at
token boundaries reduces the local context available near the token edges and
decreases inductive bias. To address this problem, we propose a 4D
Convolutional Swin Transformer, where a high-dimensional Swin …

aggregation arxiv cost cv segmentation swin transformer