End to End Trainable Active Contours via Differentiable RenderingDownload PDF

Published: 20 Dec 2019, Last Modified: 03 Apr 2024ICLR 2020 Conference Blind SubmissionReaders: Everyone
Abstract: We present an image segmentation method that iteratively evolves a polygon. At each iteration, the vertices of the polygon are displaced based on the local value of a 2D shift map that is inferred from the input image via an encoder-decoder architecture. The main training loss that is used is the difference between the polygon shape and the ground truth segmentation mask. The network employs a neural renderer to create the polygon from its vertices, making the process fully differentiable. We demonstrate that our method outperforms the state of the art segmentation networks and deep active contour solutions in a variety of benchmarks, including medical imaging and aerial images.
Code: [![github](/images/github_icon.svg) shirgur/ACDRNet](https://github.com/shirgur/ACDRNet) + [![Papers with Code](/images/pwc_icon.svg) 1 community implementation](https://paperswithcode.com/paper/?openreview=rkxawlHKDr)
Data: [Cityscapes](https://paperswithcode.com/dataset/cityscapes), [InBreast](https://paperswithcode.com/dataset/inbreast)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 1 code implementation](https://www.catalyzex.com/paper/arxiv:1912.00367/code)
Original Pdf: pdf
16 Replies