Recurrent Generic Contour-based Instance Segmentation with Progressive Learning

TL;DR

PolySnake is a novel recurrent deep network that iteratively refines object contours for accurate instance segmentation, demonstrating superior performance across multiple tasks and benchmarks.

Contribution

The paper introduces PolySnake, a new contour-based segmentation method with a recurrent refinement strategy inspired by the Snake algorithm, improving robustness and accuracy.

Findings

Outperforms existing methods on multiple benchmarks.

Effective in scene text and lane detection tasks.

Demonstrates strong generalizability across tasks.

Abstract

Contour-based instance segmentation has been actively studied, thanks to its flexibility and elegance in processing visual objects within complex backgrounds. In this work, we propose a novel deep network architecture, i.e., PolySnake, for generic contour-based instance segmentation. Motivated by the classic Snake algorithm, the proposed PolySnake achieves superior and robust segmentation performance with an iterative and progressive contour refinement strategy. Technically, PolySnake introduces a recurrent update operator to estimate the object contour iteratively. It maintains a single estimate of the contour that is progressively deformed toward the object boundary. At each iteration, PolySnake builds a semantic-rich representation for the current contour and feeds it to the recurrent operator for further contour adjustment. Through the iterative refinements, the contour progressively converges to a stable status that tightly encloses the object instance. Beyond the scope of general instance segmentation, extensive experiments are conducted to validate the effectiveness and generalizability of our PolySnake in two additional specific task scenarios, including scene text detection and lane detection. The results demonstrate that the proposed PolySnake outperforms the existing advanced methods on several multiple prevalent benchmarks across the three tasks. The codes and pre-trained models are available at https://github.com/fh2019ustc/PolySnake