Fully Convolutional Fractional Scaling
arXiv:2203.10670v1h-index: 40
Originality Synthesis-oriented
AI Analysis
This is an incremental improvement for researchers and practitioners in computer vision and deep learning who use fully convolutional networks for tasks requiring flexible scaling.
The paper tackles the problem of enabling fully convolutional networks to perform non-integer scaling, which they previously did not support, by introducing a simple and efficient architecture called FCFS.
We introduce a fully convolutional fractional scaling component, FCFS. Fully convolutional networks can be applied to any size input and previously did not support non-integer scaling. Our architecture is simple with an efficient single layer implementation. Examples and code implementations of three common scaling methods are published.