报告信息
主题：
RankSEG: A Consistent Ranking-based Framework for Segmentation
嘉宾：戴奔
地点：腾讯会议：354-748-700（或点击阅读原文）
时间：2023年08月12日（周六）19:00
报告摘要
Segmentation has emerged as a fundamental field of computer vision and natural language processing, which assigns a label to every pixel/feature to extract regions of interest from an image/text. To evaluate the performance of segmentation, the Dice and IoU metrics are used to measure the degree of overlap between the ground truth and the predicted segmentation. In this paper, we establish a theoretical foundation of segmentation with respect to the Dice/IoU metrics, including the Bayes rule and Dice/IoU-calibration, analogous to classification-calibration or Fisher consistency in classification. We prove that the existing thresholding-based framework with most operating losses are not consistent with respect to the Dice/IoU metrics, and thus may lead to a suboptimal solution. To address this pitfall, we propose a novel consistent ranking-based framework, namely RankDice/RankIoU, inspired by plug-in rules of the Bayes segmentation rule. Three numerical algorithms with GPU parallel execution are developed to implement the proposed framework in large-scale and high-dimensional segmentation. We study statistical properties of the proposed framework. We show it is Dice-/IoU-calibrated, and its excess risk bounds, and the rate of convergence are also provided. The numerical effectiveness of RankDice/mRankDice is demonstrated in various simulated examples and Fine-annotated CityScapes and Pascal VOC datasets with state-of-the-art deep learning architectures.
The slides are publicly available at https://slides.com/statmlben/rankseg/fullscreen.
嘉宾简介
Ben Dai is an Assistant Professor in the Department of Statistics at The Chinese University of Hong Kong. His main area of research includes machine learning, learning theory, statistical inference, and statistical computing. He is also interested in developing software for statistics and machine learning. Personal website: https://www.bendai.org/.
统计之都（Capital of Statistics，简称 COS）成立于 2006 年，是一个旨在推广与应用统计学、数据科学知识的公益性网站和社区。
统计之都以专业、人本、正直、团结的理念尝试推动统计和数据科学在中国的发展，促进各行业的创新和繁荣。
继续阅读
阅读原文