End-to-End Deep Convolutional Active Contours for Image Segmentation

TL;DR

This paper introduces Deep Convolutional Active Contours (DCAC), a fully end-to-end trainable image segmentation framework that unifies traditional active contours with deep learning, achieving state-of-the-art results in aerial building segmentation.

Contribution

It presents the first unified deep learning and active contour model that is end-to-end trainable for image segmentation tasks.

Findings

DCAC achieves state-of-the-art performance in aerial building segmentation.

The framework is fully differentiable and trainable end-to-end in TensorFlow.

Demonstrates significant improvement over previous methods on benchmark datasets.

Abstract

The Active Contour Model (ACM) is a standard image analysis technique whose numerous variants have attracted an enormous amount of research attention across multiple fields. Incorrectly, however, the ACM's differential-equation-based formulation and prototypical dependence on user initialization have been regarded as being largely incompatible with the recently popular deep learning approaches to image segmentation. This paper introduces the first tight unification of these two paradigms. In particular, we devise Deep Convolutional Active Contours (DCAC), a truly end-to-end trainable image segmentation framework comprising a Convolutional Neural Network (CNN) and an ACM with learnable parameters. The ACM's Eulerian energy functional includes per-pixel parameter maps predicted by the backbone CNN, which also initializes the ACM. Importantly, both the CNN and ACM components are fully implemented in TensorFlow, and the entire DCAC architecture is end-to-end automatically differentiable and backpropagation trainable without user intervention. As a challenging test case, we tackle the problem of building instance segmentation in aerial images and evaluate DCAC on two publicly available datasets, Vaihingen and Bing Huts. Our reseults demonstrate that, for building segmentation, the DCAC establishes a new state-of-the-art performance by a wide margin.