CPRAL: Collaborative Panoptic-Regional Active Learning for Semantic Segmentation

TL;DR

CPRAL introduces a collaborative active learning framework for semantic segmentation that leverages panoptic information, regional attention, and contextual labels to reduce annotation effort while maintaining high performance.

Contribution

The paper proposes a novel active learning approach combining panoptic, regional, and contextual techniques specifically for semantic segmentation, addressing class imbalance and annotation efficiency.

Findings

CPRAL outperforms state-of-the-art methods on Cityscapes and BDD10K datasets.

Achieves higher segmentation accuracy with less labeled data.

Effectively balances annotation effort and model performance.

Abstract

Acquiring the most representative examples via active learning (AL) can benefit many data-dependent computer vision tasks by minimizing efforts of image-level or pixel-wise annotations. In this paper, we propose a novel Collaborative Panoptic-Regional Active Learning framework (CPRAL) to address the semantic segmentation task. For a small batch of images initially sampled with pixel-wise annotations, we employ panoptic information to initially select unlabeled samples. Considering the class imbalance in the segmentation dataset, we import a Regional Gaussian Attention module (RGA) to achieve semantics-biased selection. The subset is highlighted by vote entropy and then attended by Gaussian kernels to maximize the biased regions. We also propose a Contextual Labels Extension (CLE) to boost regional annotations with contextual attention guidance. With the collaboration of semantics-agnostic panoptic matching and regionbiased selection and extension, our CPRAL can strike a balance between labeling efforts and performance and compromise the semantics distribution. We perform extensive experiments on Cityscapes and BDD10K datasets and show that CPRAL outperforms the cutting-edge methods with impressive results and less labeling proportion.