Mimetic Initialization of Self-Attention Layers

自注意力层的模仿初始化.

Vision Transformer Off-the-Shelf: A Surprising Baseline for Few-Shot Class-Agnostic Counting

现成的视觉Transformer：令人惊讶的少样本类别无关计数基准.

Zero-shot Object Counting

零样本目标计数.

Scale-Prior Deformable Convolution for Exemplar-Guided Class-Agnostic Counting

用于模板引导的类别无关计数的尺度先验可变形卷积.

CLIP-Count: Towards Text-Guided Zero-Shot Object Counting

CLIP-Count：文本引导的零样本目标计数.

A Low-Shot Object Counting Network With Iterative Prototype Adaptation

基于迭代原型自适应的少样本目标计数网络.